This page has only limited features, please log in for full access.

Dr. Oscar Deniz Suarez
Universidad de Castilla-La Mancha

Basic Info


Research Keywords & Expertise

0 Computer Vision
0 Deep Learning
0 Image Analysis
0 Image Processing
0 Machine Learning

Fingerprints

Computer Vision
Deep Learning
Image Processing
Machine Learning
Image Analysis

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Journal article
Published: 03 July 2021 in Electronics
Reads 0
Downloads 0

Introducing efficient automatic violence detection in video surveillance or audiovisual content monitoring systems would greatly facilitate the work of closed-circuit television (CCTV) operators, rating agencies or those in charge of monitoring social network content. In this paper we present a new deep learning architecture, using an adapted version of DenseNet for three dimensions, a multi-head self-attention layer and a bidirectional convolutional long short-term memory (LSTM) module, that allows encoding relevant spatio-temporal features, to determine whether a video is violent or not. Furthermore, an ablation study of the input frames, comparing dense optical flow and adjacent frames subtraction and the influence of the attention layer is carried out, showing that the combination of optical flow and the attention mechanism improves results up to 4.4%. The conducted experiments using four of the most widely used datasets for this problem, matching or exceeding in some cases the results of the state of the art, reducing the number of network parameters needed (4.5 millions), and increasing its efficiency in test accuracy (from 95.6% on the most complex dataset to 100% on the simplest one) and inference time (less than 0.3 s for the longest clips). Finally, to check if the generated model is able to generalize violence, a cross-dataset analysis is performed, which shows the complexity of this approach: using three datasets to train and testing on the remaining one the accuracy drops in the worst case to 70.08% and in the best case to 81.51%, which points to future work oriented towards anomaly detection in new datasets.

ACS Style

Fernando Rendón-Segador; Juan Álvarez-García; Fernando Enríquez; Oscar Deniz. ViolenceNet: Dense Multi-Head Self-Attention with Bidirectional Convolutional LSTM for Detecting Violence. Electronics 2021, 10, 1601 .

AMA Style

Fernando Rendón-Segador, Juan Álvarez-García, Fernando Enríquez, Oscar Deniz. ViolenceNet: Dense Multi-Head Self-Attention with Bidirectional Convolutional LSTM for Detecting Violence. Electronics. 2021; 10 (13):1601.

Chicago/Turabian Style

Fernando Rendón-Segador; Juan Álvarez-García; Fernando Enríquez; Oscar Deniz. 2021. "ViolenceNet: Dense Multi-Head Self-Attention with Bidirectional Convolutional LSTM for Detecting Violence." Electronics 10, no. 13: 1601.

Journal article
Published: 30 June 2021 in Applied Sciences
Reads 0
Downloads 0

There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a study based on three convolutional neural network (CNN) models applied to the automatic detection of handguns in video surveillance images. It aims to investigate the reduction of false positives by including pose information associated with the way the handguns are held in the images belonging to the training dataset. The results highlighted the best average precision (96.36%) and recall (97.23%) obtained by RetinaNet fine-tuned with the unfrozen ResNet-50 backbone and the best precision (96.23%) and F1 score values (93.36%) obtained by YOLOv3 when it was trained on the dataset including pose information. This last architecture was the only one that showed a consistent improvement—around 2%—when pose information was expressly considered during training.

ACS Style

Jesus Salido; Vanesa Lomas; Jesus Ruiz-Santaquiteria; Oscar Deniz. Automatic Handgun Detection with Deep Learning in Video Surveillance Images. Applied Sciences 2021, 11, 6085 .

AMA Style

Jesus Salido, Vanesa Lomas, Jesus Ruiz-Santaquiteria, Oscar Deniz. Automatic Handgun Detection with Deep Learning in Video Surveillance Images. Applied Sciences. 2021; 11 (13):6085.

Chicago/Turabian Style

Jesus Salido; Vanesa Lomas; Jesus Ruiz-Santaquiteria; Oscar Deniz. 2021. "Automatic Handgun Detection with Deep Learning in Video Surveillance Images." Applied Sciences 11, no. 13: 6085.

Journal article
Published: 07 May 2021 in Symmetry
Reads 0
Downloads 0

One of the most intriguing phenomenons related to deep learning is the so-called adversarial examples. These samples are visually equivalent to normal inputs, undetectable for humans, yet they cause the networks to output wrong results. The phenomenon can be framed as a symmetry/asymmetry problem, whereby inputs to a neural network with a similar/symmetric appearance to regular images, produce an opposite/asymmetric output. Some researchers are focused on developing methods for generating adversarial examples, while others propose defense methods. In parallel, there is a growing interest in characterizing the phenomenon, which is also the focus of this paper. From some well known datasets of common images, like CIFAR-10 and STL-10, a neural network architecture is first trained in a normal regime, where training and validation performances increase, reaching generalization. Additionally, the same architectures and datasets are trained in an overfitting regime, where there is a growing disparity in training and validation performances. The behaviour of these two regimes against adversarial examples is then compared. From the results, we observe greater robustness to adversarial examples in the overfitting regime. We explain this simultaneous loss of generalization and gain in robustness to adversarial examples as another manifestation of the well-known fitting-generalization trade-off.

ACS Style

Anibal Pedraza; Oscar Deniz; Gloria Bueno. On the Relationship between Generalization and Robustness to Adversarial Examples. Symmetry 2021, 13, 817 .

AMA Style

Anibal Pedraza, Oscar Deniz, Gloria Bueno. On the Relationship between Generalization and Robustness to Adversarial Examples. Symmetry. 2021; 13 (5):817.

Chicago/Turabian Style

Anibal Pedraza; Oscar Deniz; Gloria Bueno. 2021. "On the Relationship between Generalization and Robustness to Adversarial Examples." Symmetry 13, no. 5: 817.

Journal article
Published: 24 October 2020 in Entropy
Reads 0
Downloads 0

Adversarial examples are one of the most intriguing topics in modern deep learning. Imperceptible perturbations to the input can fool robust models. In relation to this problem, attack and defense methods are being developed almost on a daily basis. In parallel, efforts are being made to simply pointing out when an input image is an adversarial example. This can help prevent potential issues, as the failure cases are easily recognizable by humans. The proposal in this work is to study how chaos theory methods can help distinguish adversarial examples from regular images. Our work is based on the assumption that deep networks behave as chaotic systems, and adversarial examples are the main manifestation of it (in the sense that a slight input variation produces a totally different output). In our experiments, we show that the Lyapunov exponents (an established measure of chaoticity), which have been recently proposed for classification of adversarial examples, are not robust to image processing transformations that alter image entropy. Furthermore, we show that entropy can complement Lyapunov exponents in such a way that the discriminating power is significantly enhanced. The proposed method achieves 65% to 100% accuracy detecting adversarials with a wide range of attacks (for example: CW, PGD, Spatial, HopSkip) for the MNIST dataset, with similar results when entropy-changing image processing methods (such as Equalization, Speckle and Gaussian noise) are applied. This is also corroborated with two other datasets, Fashion-MNIST and CIFAR 19. These results indicate that classifiers can enhance their robustness against the adversarial phenomenon, being applied in a wide variety of conditions that potentially matches real world cases and also other threatening scenarios.

ACS Style

Anibal Pedraza; Oscar Deniz; Gloria Bueno. Approaching Adversarial Example Classification with Chaos Theory. Entropy 2020, 22, 1201 .

AMA Style

Anibal Pedraza, Oscar Deniz, Gloria Bueno. Approaching Adversarial Example Classification with Chaos Theory. Entropy. 2020; 22 (11):1201.

Chicago/Turabian Style

Anibal Pedraza; Oscar Deniz; Gloria Bueno. 2020. "Approaching Adversarial Example Classification with Chaos Theory." Entropy 22, no. 11: 1201.

Original article
Published: 26 February 2020 in International Journal of Machine Learning and Cybernetics
Reads 0
Downloads 0

Deep learning (henceforth DL) has become most powerful machine learning methodology. Under specific circumstances recognition rates even surpass those obtained by humans. Despite this, several works have shown that deep learning produces outputs that are very far from human responses when confronted with the same task. This the case of the so-called “adversarial examples” (henceforth AE). The fact that such implausible misclassifications exist points to a fundamental difference between machine and human learning. This paper focuses on the possible causes of this intriguing phenomenon. We first argue that the error in adversarial examples is caused by high bias, i.e. by regularization that has local negative effects. This idea is supported by our experiments in which the robustness to adversarial examples is measured with respect to the level of fitting to training samples. Higher fitting was associated to higher robustness to adversarial examples. This ties the phenomenon to the trade-off that exists in machine learning between fitting and generalization.

ACS Style

Oscar Deniz; Anibal Pedraza; Noelia Vallez; Jesus Salido; Gloria Bueno. Robustness to adversarial examples can be improved with overfitting. International Journal of Machine Learning and Cybernetics 2020, 11, 935 -944.

AMA Style

Oscar Deniz, Anibal Pedraza, Noelia Vallez, Jesus Salido, Gloria Bueno. Robustness to adversarial examples can be improved with overfitting. International Journal of Machine Learning and Cybernetics. 2020; 11 (4):935-944.

Chicago/Turabian Style

Oscar Deniz; Anibal Pedraza; Noelia Vallez; Jesus Salido; Gloria Bueno. 2020. "Robustness to adversarial examples can be improved with overfitting." International Journal of Machine Learning and Cybernetics 11, no. 4: 935-944.

Journal article
Published: 31 January 2020 in Sensors
Reads 0
Downloads 0

An automatic “museum audio guide” is presented as a new type of audio guide for museums. The device consists of a headset equipped with a camera that captures exhibit pictures and the eyes of things computer vision device (EoT). The EoT board is capable of recognizing artworks using features from accelerated segment test (FAST) keypoints and a random forest classifier, and is able to be used for an entire day without the need to recharge the batteries. In addition, an application logic has been implemented, which allows for a special highly-efficient behavior upon recognition of the painting. Two different use case scenarios have been implemented. The main testing was performed with a piloting phase in a real world museum. Results show that the system keeps its promises regarding its main benefit, which is simplicity of use and the user’s preference of the proposed system over traditional audioguides.

ACS Style

Noelia Vallez; Stephan Krauss; Jose Luis Espinosa-Aranda; Alain Pagani; Kasra Seirafi; Oscar Deniz. Automatic Museum Audio Guide. Sensors 2020, 20, 779 .

AMA Style

Noelia Vallez, Stephan Krauss, Jose Luis Espinosa-Aranda, Alain Pagani, Kasra Seirafi, Oscar Deniz. Automatic Museum Audio Guide. Sensors. 2020; 20 (3):779.

Chicago/Turabian Style

Noelia Vallez; Stephan Krauss; Jose Luis Espinosa-Aranda; Alain Pagani; Kasra Seirafi; Oscar Deniz. 2020. "Automatic Museum Audio Guide." Sensors 20, no. 3: 779.

Journal article
Published: 19 December 2019 in Computer Methods and Programs in Biomedicine
Reads 0
Downloads 0

Background and Objective: Glomeruli identification, i.e., detection and characterization, is a key procedure in many nephropathology studies. In this paper, semantic segmentation based on convolutional neural networks (CNN) is proposed to detect glomeruli using Whole Slide Imaging (WSI) follows by a classification CNN to divide the glomeruli into normal and sclerosed. Methods: Comparison between U-Net and SegNet CNNs is performed for pixel-level segmentation considering both a two and three class problem, that is, a) non-glomerular and glomerular structures and b) non-glomerular normal glomerular and sclerotic structures. The two class semantic segmentation result is then used for a CNN classification where glomerular regions are divided into normal and global sclerosed glomeruli. Results: These methods were tested on a dataset composed of 47 WSIs belonging to human kidney sections stained with Periodic Acid Schiff (PAS). The best approach was the SegNet for two class segmentation follows by a fine-tuned AlexNet network to characterize the glomeruli. 98.16% of accuracy was obtained with this process of consecutive CNNs (SegNet-AlexNet) for segmentation and classification. Conclusion: The results obtained demonstrate that the sequential CNN segmentation-classification strategy achieves higher accuracy reducing misclassified cases and therefore being the methodology proposed for glomerulosclerosis detection.

ACS Style

Gloria Bueno; M. Milagro Fernandez-Carrobles; Lucia Gonzalez-Lopez; Oscar Deniz. Glomerulosclerosis identification in whole slide images using semantic segmentation. Computer Methods and Programs in Biomedicine 2019, 184, 105273 .

AMA Style

Gloria Bueno, M. Milagro Fernandez-Carrobles, Lucia Gonzalez-Lopez, Oscar Deniz. Glomerulosclerosis identification in whole slide images using semantic segmentation. Computer Methods and Programs in Biomedicine. 2019; 184 ():105273.

Chicago/Turabian Style

Gloria Bueno; M. Milagro Fernandez-Carrobles; Lucia Gonzalez-Lopez; Oscar Deniz. 2019. "Glomerulosclerosis identification in whole slide images using semantic segmentation." Computer Methods and Programs in Biomedicine 184, no. : 105273.

Journal article
Published: 08 October 2019 in Engineering Applications of Artificial Intelligence
Reads 0
Downloads 0

Microscopic algae segmentation, specifically of diatoms, is an essential procedure for water quality assessment. The segmentation of these microalgae is still a challenge for computer vision. This paper addresses for the first time this problem using deep learning approaches to predict exactly those pixels that belong to each class, i.e., diatom and non diatom. A comparison between semantic segmentation and instance segmentation is carried out, and the performance of these methods is evaluated in the presence of different types of noise. The trained models are then evaluated with the same raw images used for manual diatom identification. A total of 126 images of the entire field of view at 60x magnification, with a size of 2592x1944 pixels, are analyzed. The images contain 10 different taxa plus debris and fragments. The best results were obtained with instance segmentation achieving an average precision of 85% with 86% sensitivity and 91% specificity (up to 92% precision with 98%, both sensitivity and specificity for some taxa). Semantic segmentation was able to improve the average sensitivity up to 95% but decreasing the specificity down to 60% and precision to 57%. Instance segmentation was also able to properly separate diatoms when overlap occurs, which helps estimate the number of diatoms, a key requirement for water quality grading.

ACS Style

Jesus Ruiz-Santaquiteria; Gloria Bueno; Oscar Deniz; Noelia Vallez; Gabriel Cristobal. Semantic versus instance segmentation in microscopic algae detection. Engineering Applications of Artificial Intelligence 2019, 87, 103271 .

AMA Style

Jesus Ruiz-Santaquiteria, Gloria Bueno, Oscar Deniz, Noelia Vallez, Gabriel Cristobal. Semantic versus instance segmentation in microscopic algae detection. Engineering Applications of Artificial Intelligence. 2019; 87 ():103271.

Chicago/Turabian Style

Jesus Ruiz-Santaquiteria; Gloria Bueno; Oscar Deniz; Noelia Vallez; Gabriel Cristobal. 2019. "Semantic versus instance segmentation in microscopic algae detection." Engineering Applications of Artificial Intelligence 87, no. : 103271.

Journal article
Published: 01 October 2019 in Computer Methods and Programs in Biomedicine
Reads 0
Downloads 0

Digital scanners are being increasingly adopt-ed in anatomical pathology, but there is still a lack of a standardized whole slide image (WSI) format. This translates into the need for interoperability and knowledge representation for shareable and computable clinical information. This work describes a robust solution, called Visilab Viewer, able to interact and work with any WSI based on the DICOM standard. Visilab Viewer is a web platform developed and integrated alongside a proposed web architecture following the DICOM definition. To prepare the information of the pyramid structure proposed in DICOM, a specific module was defined. The same structure is used by a second module that aggregates on the cache browser the adjacent tiles or frames of the current user's viewport with the aim of achieving fast and fluid navigation over the tissue slide. This solution was tested and compared with three different web viewers, publicly available, with 10 WSIs. A quantitative assessment was performed based on the average load time per frame together with the number of fully loaded frames. Kruskal-Wallis and Dunn tests were used to compare each web viewer latency results and finally to rank them. Additionally, a qualitative evaluation was done by 6 pathologists based on speed and quality for zooming, panning and usability. The proposed viewer obtained the best performance in both assessments. The entire architecture proposed was tested in the 2nd worldwide DICOM Connectathon, obtaining successful results with all participant scanner vendors. The online tool allows users to navigate and obtain a correct visualization of the samples avoiding any restriction of format and localization. The two strategical modules allow to reduce time in displaying the slide and therefore, offer high fluidity and usability. The web platform manages not only the visualization with the developed web viewer but also includes the insertion, manipulation and generation of new DICOM elements. Visilab Viewer can successfully exchange DICOM data. Connectathons are the ultimate interoperability tests and are therefore required to guarantee that solutions as Visilab Viewer and its architecture can successfully exchange data following the DICOM standard. Accompanying demo video. (Link to Youtube video.).

ACS Style

Nieves Lajara; Jose Luis Espinosa-Aranda; Oscar Deniz; Gloria Bueno. Optimum web viewer application for DICOM whole slide image visualization in anatomical pathology. Computer Methods and Programs in Biomedicine 2019, 179, 104983 .

AMA Style

Nieves Lajara, Jose Luis Espinosa-Aranda, Oscar Deniz, Gloria Bueno. Optimum web viewer application for DICOM whole slide image visualization in anatomical pathology. Computer Methods and Programs in Biomedicine. 2019; 179 ():104983.

Chicago/Turabian Style

Nieves Lajara; Jose Luis Espinosa-Aranda; Oscar Deniz; Gloria Bueno. 2019. "Optimum web viewer application for DICOM whole slide image visualization in anatomical pathology." Computer Methods and Programs in Biomedicine 179, no. : 104983.

Conference paper
Published: 22 September 2019 in Transactions on Petri Nets and Other Models of Concurrency XV
Reads 0
Downloads 0

The development of object detection systems is normally driven to achieve both high detection and low false positive rates in a certain public dataset. However, when put into a real scenario the result is generally an unacceptable rate of false alarms. In this context we propose to add an additional step that models and filters the typical false alarms of the new scenario while roughly maintaining the ability to detect the objects of interest. We propose to use the false alarms of the new scenario to train a deep autoencoder and to model them. The latter will act as a filter that checks whether the output of the detector is one of its typical false positives or not based on the reconstruction error measured with the Mean Squared Error (MSE) and the Peak Signal-to-Noise Ratio (PSNR). We test the system using an entirely synthetic novel dataset for training and testing the autoencoder generated with Unreal Engine 4. Results show a reduction in the number of FPs of up to 37.9% in combination with the PSNR error while maintaining the same detection capability.

ACS Style

Noelia Vallez; Alberto Velasco-Mata; Juan Jose Corroto; Oscar Deniz. Weapon Detection for Particular Scenarios Using Deep Learning. Transactions on Petri Nets and Other Models of Concurrency XV 2019, 371 -382.

AMA Style

Noelia Vallez, Alberto Velasco-Mata, Juan Jose Corroto, Oscar Deniz. Weapon Detection for Particular Scenarios Using Deep Learning. Transactions on Petri Nets and Other Models of Concurrency XV. 2019; ():371-382.

Chicago/Turabian Style

Noelia Vallez; Alberto Velasco-Mata; Juan Jose Corroto; Oscar Deniz. 2019. "Weapon Detection for Particular Scenarios Using Deep Learning." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 371-382.

Conference paper
Published: 22 September 2019 in Lecture Notes in Computer Science
Reads 0
Downloads 0

Diatom identification is a crucial process to estimate water quality, which is essential in biological studies. This process can be automated with machine learning algorithms. For this purpose, a dataset with 10 common taxa is collected, with annotations provided by an expert diatomist. In this work, a comparison of the classical state-of-the-art general purpose methods along with two different deep learning approaches is carried out. The classical methods are based on Viola-Jones and scale and curvature invariant ridge object detectors. The deep learning based methods are Semantic Segmentation and YOLO. This is the first time that Viola-Jones and Semantic Segmentation techniques are applied and compared for diatom segmentation in microscopic images containing several taxon shells. While all methods provide relatively good results in specific species, the deep learning approaches are consistently better in terms of sensitivity and specificity (up to 0.99 for some taxa) and up to 0.86 precision.

ACS Style

Jesús Ruiz-Santaquitaria; Anibal Pedraza; Carlos Sánchez; José A. Libreros; Jesús Salido; Oscar Deniz; Saúl Blanco; Gabriel Cristóbal; Gloria Bueno. Deep Learning Versus Classic Methods for Multi-taxon Diatom Segmentation. Lecture Notes in Computer Science 2019, 342 -354.

AMA Style

Jesús Ruiz-Santaquitaria, Anibal Pedraza, Carlos Sánchez, José A. Libreros, Jesús Salido, Oscar Deniz, Saúl Blanco, Gabriel Cristóbal, Gloria Bueno. Deep Learning Versus Classic Methods for Multi-taxon Diatom Segmentation. Lecture Notes in Computer Science. 2019; ():342-354.

Chicago/Turabian Style

Jesús Ruiz-Santaquitaria; Anibal Pedraza; Carlos Sánchez; José A. Libreros; Jesús Salido; Oscar Deniz; Saúl Blanco; Gabriel Cristóbal; Gloria Bueno. 2019. "Deep Learning Versus Classic Methods for Multi-taxon Diatom Segmentation." Lecture Notes in Computer Science , no. : 342-354.

Conference paper
Published: 22 September 2019 in Lecture Notes in Computer Science
Reads 0
Downloads 0

Public safety in public areas is nowadays one of the main concerns for governments and companies around the world. Video surveillance systems can take advantage from the emerging techniques of deep learning to improve their performance and accuracy detecting possible threats. This paper presents a system for gun and knife detection based on the Faster R-CNN methodology. Two approaches have been compared taking as CNN base a GoogleNet and a SqueezeNet architecture respectively. The best result for gun detection was obtained using a SqueezeNet architecture achieving a 85.44% \(AP_{50}\). For knife detection, the GoogleNet approach achieved a 46.68% \(AP_{50}\). Both results improve upon previous literature results evidencing the effectiveness of our detectors.

ACS Style

M. Milagro Fernandez-Carrobles; Oscar Deniz; Fernando Maroto. Gun and Knife Detection Based on Faster R-CNN for Video Surveillance. Lecture Notes in Computer Science 2019, 441 -452.

AMA Style

M. Milagro Fernandez-Carrobles, Oscar Deniz, Fernando Maroto. Gun and Knife Detection Based on Faster R-CNN for Video Surveillance. Lecture Notes in Computer Science. 2019; ():441-452.

Chicago/Turabian Style

M. Milagro Fernandez-Carrobles; Oscar Deniz; Fernando Maroto. 2019. "Gun and Knife Detection Based on Faster R-CNN for Video Surveillance." Lecture Notes in Computer Science , no. : 441-452.

Conference paper
Published: 08 June 2019 in Transactions on Petri Nets and Other Models of Concurrency XV
Reads 0
Downloads 0

Law enforcement agencies and private security companies work to prevent, detect and counteract any threat with the resources they have, including alarms and video surveillance. Even so, there are still terrorist attacks or shootings in schools in which armed people move around a venue exercising violence and generating victims, showing the limitations of current systems. For example, they force security agents to monitor continuously all the images coming from the installed cameras, and potential victims nearby are not aware of the danger until someone triggers a general alarm, which also does not give them information on what to do to protect themselves. In this article we present a project that is being developed to apply the latest technologies in early threat detection and optimal response. The system is based on the automatic processing of video surveillance images to detect weapons and a mobile app that serves both for detection through the analysis of mobile device sensors, and to send users personalised and dynamic indications. The objective is to react in the shortest possible time and minimise the damage suffered.

ACS Style

Fernando Enríquez; Luis Miguel Soria; Juan Antonio Álvarez-García; Fernando Sancho Caparrini; Francisco Velasco; Oscar Deniz; Noelia Vallez. Vision and Crowdsensing Technology for an Optimal Response in Physical-Security. Transactions on Petri Nets and Other Models of Concurrency XV 2019, 15 -26.

AMA Style

Fernando Enríquez, Luis Miguel Soria, Juan Antonio Álvarez-García, Fernando Sancho Caparrini, Francisco Velasco, Oscar Deniz, Noelia Vallez. Vision and Crowdsensing Technology for an Optimal Response in Physical-Security. Transactions on Petri Nets and Other Models of Concurrency XV. 2019; ():15-26.

Chicago/Turabian Style

Fernando Enríquez; Luis Miguel Soria; Juan Antonio Álvarez-García; Fernando Sancho Caparrini; Francisco Velasco; Oscar Deniz; Noelia Vallez. 2019. "Vision and Crowdsensing Technology for an Optimal Response in Physical-Security." Transactions on Petri Nets and Other Models of Concurrency XV , no. : 15-26.

Conference paper
Published: 16 May 2019 in Lecture Notes in Computer Science
Reads 0
Downloads 0

In recent scientific literature, some studies have been published where recognition rates obtained with Deep Learning (DL) surpass those obtained by humans on the same task. In contrast to this, other studies have shown that DL networks have a somewhat strange behavior which is very different from human responses when confronted with the same task. The case of the so-called “adversarial examples” is perhaps the best example in this regard. Despite the biological plausibility of neural networks, the fact that they can produce such implausible misclassifications still points to a fundamental difference between human and machine learning. This paper delves into the possible causes of this intriguing phenomenon. We first contend that, if adversarial examples are pointing to an implausibility it is because our perception of them relies on our capability to recognise the classes of the images. For this reason we focus on what we call cognitively adversarial examples, which are those obtained from samples that the classifier can in fact recognise correctly. Additionally, in this paper we argue that the phenomenon of adversarial examples is rooted in the inescapable trade-off that exists in machine learning (including DL) between fitting and generalization. This hypothesis is supported by experiments carried out in which the robustness to adversarial examples is measured with respect to the degree of fitting to the training samples.

ACS Style

Oscar Deniz; Noelia Vallez; Gloria Bueno. Adversarial Examples are a Manifestation of the Fitting-Generalization Trade-off. Lecture Notes in Computer Science 2019, 569 -580.

AMA Style

Oscar Deniz, Noelia Vallez, Gloria Bueno. Adversarial Examples are a Manifestation of the Fitting-Generalization Trade-off. Lecture Notes in Computer Science. 2019; ():569-580.

Chicago/Turabian Style

Oscar Deniz; Noelia Vallez; Gloria Bueno. 2019. "Adversarial Examples are a Manifestation of the Fitting-Generalization Trade-off." Lecture Notes in Computer Science , no. : 569-580.

Journal article
Published: 07 September 2018 in Symmetry
Reads 0
Downloads 0

Computer vision and deep learning are clearly demonstrating a capability to create engaging cognitive applications and services. However, these applications have been mostly confined to powerful Graphic Processing Units (GPUs) or the cloud due to their demanding computational requirements. Cloud processing has obvious bandwidth, energy consumption and privacy issues. The Eyes of Things (EoT) is a powerful and versatile embedded computer vision platform which allows the user to develop artificial vision and deep learning applications that analyse images locally. In this article, we use the deep learning capabilities of an EoT device for a real-life facial informatics application: a doll capable of recognizing emotions, using deep learning techniques, and acting accordingly. The main impact and significance of the presented application is in showing that a toy can now do advanced processing locally, without the need of further computation in the cloud, thus reducing latency and removing most of the ethical issues involved. Finally, the performance of the convolutional neural network developed for that purpose is studied and a pilot was conducted on a panel of 12 children aged between four and ten years old to test the doll.

ACS Style

Jose Luis Espinosa-Aranda; Noelia Vallez; Jose Maria Rico-Saavedra; Javier Parra-Patino; Gloria Bueno; Matteo Sorci; David Moloney; Dexmont Pena; Oscar Deniz. Smart Doll: Emotion Recognition Using Embedded Deep Learning. Symmetry 2018, 10, 387 .

AMA Style

Jose Luis Espinosa-Aranda, Noelia Vallez, Jose Maria Rico-Saavedra, Javier Parra-Patino, Gloria Bueno, Matteo Sorci, David Moloney, Dexmont Pena, Oscar Deniz. Smart Doll: Emotion Recognition Using Embedded Deep Learning. Symmetry. 2018; 10 (9):387.

Chicago/Turabian Style

Jose Luis Espinosa-Aranda; Noelia Vallez; Jose Maria Rico-Saavedra; Javier Parra-Patino; Gloria Bueno; Matteo Sorci; David Moloney; Dexmont Pena; Oscar Deniz. 2018. "Smart Doll: Emotion Recognition Using Embedded Deep Learning." Symmetry 10, no. 9: 387.

Journal article
Published: 08 June 2018 in IEEE Transactions on Image Processing
Reads 0
Downloads 0

While action recognition has become an important line of research in computer vision, the recognition of particular events, such as aggressive behaviors, or fights, has been relatively less studied. These tasks may be extremely useful in several video surveillance scenarios, such as psychiatric wards, prisons, or even in personal camera smartphones. Their potential usability has led to a surge of interest in developing fight or violence detectors. One of the key aspects in this case is efficiency, that is, these methods should be computationally fast. “Handcrafted” spatio-temporal features that account for both motion and appearance information can achieve high accuracy rates, albeit the computational cost of extracting some of those features is still prohibitive for practical applications. The deep learning paradigm has been recently applied for the first time to this task too, in the form of a 3D convolutional neural network that processes the whole video sequence as input. However, results in human perception of other's actions suggest that, in this specific task, motion features are crucial. This means that using the whole video as input may add both redundancy and noise in the learning process. In this paper, we propose a hybrid “handcrafted/learned” feature framework which provides better accuracy than the previous feature learning method, with similar computational efficiency. The proposed method is compared to three related benchmark data sets. The method outperforms the different state-of-the-art methods in two of the three considered benchmark data sets.

ACS Style

Ismael Serrano; Oscar Deniz; Jose Luis Espinosa-Aranda; Gloria Bueno. Fight Recognition in Video Using Hough Forests and 2D Convolutional Neural Network. IEEE Transactions on Image Processing 2018, 27, 4787 -4797.

AMA Style

Ismael Serrano, Oscar Deniz, Jose Luis Espinosa-Aranda, Gloria Bueno. Fight Recognition in Video Using Hough Forests and 2D Convolutional Neural Network. IEEE Transactions on Image Processing. 2018; 27 (10):4787-4797.

Chicago/Turabian Style

Ismael Serrano; Oscar Deniz; Jose Luis Espinosa-Aranda; Gloria Bueno. 2018. "Fight Recognition in Video Using Hough Forests and 2D Convolutional Neural Network." IEEE Transactions on Image Processing 27, no. 10: 4787-4797.

Conference paper
Published: 24 May 2018 in Optics, Photonics, and Digital Technologies for Imaging Applications V
Reads 0
Downloads 0

Diatom detection has been a challenging task for computer scientist and biologist during past years. In this work, the new state of art techniques based on the deep learning framework have been tested, in order to check whether they are suitable for this purpose. On the one hand, RCNNs (Region based Convolutional Neural Networks), which select candidate regions and applies a convolutional neural network and, on the other hand, YOLO (You Only Look Once), which applies a single neural network over the whole image, have been tested. The first one is able to reach poor results in out experimentation, with an average of 0.68 recall and some tricky aspects, as for example it is needed to apply a bounding box merging algorithm to get stable detections; but the second one gets remarkable results, with an average of 0.84 recall in the evaluation that have been carried out, and less aspects to take into account after the detection has been performed. Future work related to parameter tuning and processing are needed to increase the performance of deep learning in the detection task. However, as for classification it has been probed to provide succesfully performance.

ACS Style

Gloria Bueno; Oscar Déniz; Jesus Ruiz-Santaquiteria; Adriana Olenici; Gabriel Cristobal; Anibal Pedraza; Carlos Sanchez; Saúl Blanco; Maria Borrego-Ramos. Lights and pitfalls of convolutional neural networks for diatom identification. Optics, Photonics, and Digital Technologies for Imaging Applications V 2018, 10679, 106790G .

AMA Style

Gloria Bueno, Oscar Déniz, Jesus Ruiz-Santaquiteria, Adriana Olenici, Gabriel Cristobal, Anibal Pedraza, Carlos Sanchez, Saúl Blanco, Maria Borrego-Ramos. Lights and pitfalls of convolutional neural networks for diatom identification. Optics, Photonics, and Digital Technologies for Imaging Applications V. 2018; 10679 ():106790G.

Chicago/Turabian Style

Gloria Bueno; Oscar Déniz; Jesus Ruiz-Santaquiteria; Adriana Olenici; Gabriel Cristobal; Anibal Pedraza; Carlos Sanchez; Saúl Blanco; Maria Borrego-Ramos. 2018. "Lights and pitfalls of convolutional neural networks for diatom identification." Optics, Photonics, and Digital Technologies for Imaging Applications V 10679, no. : 106790G.

Journal article
Published: 02 January 2018 in Journal of Biomedical Optics
Reads 0
Downloads 0

We study the effectiveness of several low-cost oblique illumination filters to improve overall image quality, in comparison with standard bright field imaging. For this purpose, a dataset composed of 3360 diatom images belonging to 21 taxa was acquired. Subjective and objective image quality assessments were done. The subjective evaluation was performed by a group of diatom experts by psychophysical test where resolution, focus, and contrast were assessed. Moreover, some objective nonreference image quality metrics were applied to the same image dataset to complete the study, together with the calculation of several texture features to analyze the effect of these filters in terms of textural properties. Both image quality evaluation methods, subjective and objective, showed better results for images acquired using these illumination filters in comparison with the no filtered image. These promising results confirm that this kind of illumination filters can be a practical way to improve the image quality, thanks to the simple and low cost of the design and manufacturing process.

ACS Style

Jesus Ruiz-Santaquiteria; Jose Luis Espinosa-Aranda; Oscar Deniz; Carlos Sanchez; Maria Borrego-Ramos; Saul Blanco; Gabriel Cristobal; Gloria Bueno. Low-cost oblique illumination: an image quality assessment. Journal of Biomedical Optics 2018, 23, 016001 -14.

AMA Style

Jesus Ruiz-Santaquiteria, Jose Luis Espinosa-Aranda, Oscar Deniz, Carlos Sanchez, Maria Borrego-Ramos, Saul Blanco, Gabriel Cristobal, Gloria Bueno. Low-cost oblique illumination: an image quality assessment. Journal of Biomedical Optics. 2018; 23 (1):016001-14.

Chicago/Turabian Style

Jesus Ruiz-Santaquiteria; Jose Luis Espinosa-Aranda; Oscar Deniz; Carlos Sanchez; Maria Borrego-Ramos; Saul Blanco; Gabriel Cristobal; Gloria Bueno. 2018. "Low-cost oblique illumination: an image quality assessment." Journal of Biomedical Optics 23, no. 1: 016001-14.

Original investigation
Published: 12 December 2017 in JAMA
Reads 0
Downloads 0

Quiz Ref IDFull digitalization of the microscopic evaluation of stained tissue sections in histopathology has become feasible in recent years because of advances in slide scanning technology and cost reduction in digital storage. Advantages of digital pathology include remote diagnostics, immediate availability of archival cases, and easier consultations with expert pathologists.1 Also, the possibility for computer-aided diagnostics may be advantageous.2

ACS Style

Babak Ehteshami Bejnordi; Mitko Veta; Paul Johannes Van Diest; Bram Van Ginneken; Nico Karssemeijer; Geert Litjens; Jeroen A. W. M. Van Der Laak; Meyke Hermsen; Quirine F Manson; Maschenka Balkenhol; Oscar Geessink; Nikolaos Stathonikos; Marcory Crf Van Dijk; Peter Bult; Francisco Beca; Andrew H Beck; Dayong Wang; Aditya Khosla; Rishab Gargeya; Humayun Irshad; Aoxiao Zhong; Qi Dou; Khvatkov Vitali; Balkenhol Maschenka; Huang-Jing Lin; Pheng Ann Heng; Christian Haß; Elia Bruni; Quincy Wong; Ugur Halici; Mustafa Ümit Öner; Rengul Cetin-Atalay; Matt Berseth; Vitali Khvatkov; Alexei Vylegzhanin; Oren Kraus; Muhammad Shaban; Nasir Rajpoot; Ruqayya Awan; Korsuk Sirinukunwattana; Talha Qaiser; Yee-Wah Tsang; David Tellez; Jonas Annuscheit; Peter Hufnagl; Mira Valkonen; Kimmo Kartasalo; Leena Latonen; Pekka Ruusuvuori; Kaisa Maria Liimatainen; Shadi Albarqouni; Bharti Mungal; Ami George; Stefanie Demirci; Nassir Navab; Seiryo Watanabe; Shigeto Seno; Yoichi Takenaka; Hideo Matsuda; Hady Ahmady Phoulady; Vassili Kovalev; Alexander Kalinovsky; Vitali Liauchuk; Gloria Bueno; Mª Del Milagro Fernández-Carrobles; Ismael Serrano; Oscar Deniz; Daniel Racoceanu; Rui Venâncio. Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer. JAMA 2017, 318, 2199 -2210.

AMA Style

Babak Ehteshami Bejnordi, Mitko Veta, Paul Johannes Van Diest, Bram Van Ginneken, Nico Karssemeijer, Geert Litjens, Jeroen A. W. M. Van Der Laak, Meyke Hermsen, Quirine F Manson, Maschenka Balkenhol, Oscar Geessink, Nikolaos Stathonikos, Marcory Crf Van Dijk, Peter Bult, Francisco Beca, Andrew H Beck, Dayong Wang, Aditya Khosla, Rishab Gargeya, Humayun Irshad, Aoxiao Zhong, Qi Dou, Khvatkov Vitali, Balkenhol Maschenka, Huang-Jing Lin, Pheng Ann Heng, Christian Haß, Elia Bruni, Quincy Wong, Ugur Halici, Mustafa Ümit Öner, Rengul Cetin-Atalay, Matt Berseth, Vitali Khvatkov, Alexei Vylegzhanin, Oren Kraus, Muhammad Shaban, Nasir Rajpoot, Ruqayya Awan, Korsuk Sirinukunwattana, Talha Qaiser, Yee-Wah Tsang, David Tellez, Jonas Annuscheit, Peter Hufnagl, Mira Valkonen, Kimmo Kartasalo, Leena Latonen, Pekka Ruusuvuori, Kaisa Maria Liimatainen, Shadi Albarqouni, Bharti Mungal, Ami George, Stefanie Demirci, Nassir Navab, Seiryo Watanabe, Shigeto Seno, Yoichi Takenaka, Hideo Matsuda, Hady Ahmady Phoulady, Vassili Kovalev, Alexander Kalinovsky, Vitali Liauchuk, Gloria Bueno, Mª Del Milagro Fernández-Carrobles, Ismael Serrano, Oscar Deniz, Daniel Racoceanu, Rui Venâncio. Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer. JAMA. 2017; 318 (22):2199-2210.

Chicago/Turabian Style

Babak Ehteshami Bejnordi; Mitko Veta; Paul Johannes Van Diest; Bram Van Ginneken; Nico Karssemeijer; Geert Litjens; Jeroen A. W. M. Van Der Laak; Meyke Hermsen; Quirine F Manson; Maschenka Balkenhol; Oscar Geessink; Nikolaos Stathonikos; Marcory Crf Van Dijk; Peter Bult; Francisco Beca; Andrew H Beck; Dayong Wang; Aditya Khosla; Rishab Gargeya; Humayun Irshad; Aoxiao Zhong; Qi Dou; Khvatkov Vitali; Balkenhol Maschenka; Huang-Jing Lin; Pheng Ann Heng; Christian Haß; Elia Bruni; Quincy Wong; Ugur Halici; Mustafa Ümit Öner; Rengul Cetin-Atalay; Matt Berseth; Vitali Khvatkov; Alexei Vylegzhanin; Oren Kraus; Muhammad Shaban; Nasir Rajpoot; Ruqayya Awan; Korsuk Sirinukunwattana; Talha Qaiser; Yee-Wah Tsang; David Tellez; Jonas Annuscheit; Peter Hufnagl; Mira Valkonen; Kimmo Kartasalo; Leena Latonen; Pekka Ruusuvuori; Kaisa Maria Liimatainen; Shadi Albarqouni; Bharti Mungal; Ami George; Stefanie Demirci; Nassir Navab; Seiryo Watanabe; Shigeto Seno; Yoichi Takenaka; Hideo Matsuda; Hady Ahmady Phoulady; Vassili Kovalev; Alexander Kalinovsky; Vitali Liauchuk; Gloria Bueno; Mª Del Milagro Fernández-Carrobles; Ismael Serrano; Oscar Deniz; Daniel Racoceanu; Rui Venâncio. 2017. "Diagnostic Assessment of Deep Learning Algorithms for Detection of Lymph Node Metastases in Women With Breast Cancer." JAMA 318, no. 22: 2199-2210.

Original paper
Published: 07 December 2017 in Machine Vision and Applications
Reads 0
Downloads 0

While action recognition has become an important line of research in computer vision, the recognition of particular events such as aggressive behaviors, or fights, has been relatively less studied. These tasks may be exceedingly useful in some video surveillance scenarios such as psychiatric centers, prisons or even in personal camera smartphones. Their potential usability has caused a surge of interest in developing fight or violence detectors. The key aspect in this case is efficiency, that is, these methods should be computationally very fast. In this paper, spatio-temporal elastic cuboid trajectories are proposed for fight recognition. This method is based on the use of blob movements to create trajectories that capture and model the different motions that are specific to a fight. The proposed method is robust to the specific shapes and positions of the individuals. Additionally, the standard Hough forests classifier is adapted in order to use it with this descriptor. This method is compared to other nine related methods on four datasets. The results show that the proposed method obtains the best accuracy for each dataset and is also computationally efficient.

ACS Style

Ismael Serrano; Oscar Deniz; Gloria Bueno; Guillermo Garcia-Hernando; Tae-Kyun Kim. Spatio-temporal elastic cuboid trajectories for efficient fight recognition using Hough forests. Machine Vision and Applications 2017, 29, 207 -217.

AMA Style

Ismael Serrano, Oscar Deniz, Gloria Bueno, Guillermo Garcia-Hernando, Tae-Kyun Kim. Spatio-temporal elastic cuboid trajectories for efficient fight recognition using Hough forests. Machine Vision and Applications. 2017; 29 (2):207-217.

Chicago/Turabian Style

Ismael Serrano; Oscar Deniz; Gloria Bueno; Guillermo Garcia-Hernando; Tae-Kyun Kim. 2017. "Spatio-temporal elastic cuboid trajectories for efficient fight recognition using Hough forests." Machine Vision and Applications 29, no. 2: 207-217.