Ouiem Bchir

Dr. Ouiem Bchir

Computer Science Department, Department of Computer Science, College of Computer and Information Sciences, King Saud University, Riyadh, Ar Riyāḑ, Saudi Arabia
orcid
avatar
Co-authors
avatar
Following
avatar
Followers

Research Focus & Metrics

Explore full metrics on Scilit

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
22 March 2024 in Cancers
Verified
Journal Article
Open access
PDF file
NANasser Alsadhan
Nasser Alsadhan
SAShatha Ali Alamri
Shatha Ali Alamri
MIMohamed Maher Ben Ismail
Mohamed Maher Ben Ismail
OBOuiem Bchir
Ouiem Bchir
The incidence of skin cancer is rising globally, posing a significant public health threat. An early and accurate diagnosis is crucial for patient prognoses. However, discriminating between malignant melanoma and benign lesions, such as nevi and keratoses, remains a challenging task due to their visual similarities. Image-based recognition systems offer a promising solution to aid dermatologists and potentially reduce unnecessary biopsies. This research investigated the performance of four unified convolutional neural networks, namely, YOLOv3, YOLOv4, YOLOv5, and YOLOv7, in classifying skin lesions. Each model was trained on a benchmark dataset, and the obtained performances were compared based on lesion localization, classification accuracy, and inference time. In particular, YOLOv7 achieved superior performance with an Intersection over Union (IoU) of 86.3%, a mean Average Precision (mAP) of 75.4%, an F1-measure of 80%, and an inference time of 0.32 s per image. These findings demonstrated the potential of YOLOv7 as a valuable tool for aiding dermatologists in early skin cancer diagnosis and potentially reducing unnecessary biopsies.
17 January 2020 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
AAAbeer Almohamade
Abeer Almohamade
OBOuiem Bchir
Ouiem Bchir
MIMohamed Maher Ben Ismail
Mohamed Maher Ben Ismail
We propose a novel multiple query retrieval approach, named weight-learner, which relies on visual feature discrimination to estimate the distances between the query images and images in the database. For each query image, this discrimination consists of learning, in an unsupervised manner, the optimal relevance weight for each visual feature/descriptor. These feature relevance weights are designed to reduce the semantic gap between the extracted visual features and the user’s high-level semantics. We mathematically formulate the proposed solution through the minimization of some objective functions. This optimization aims to produce optimal feature relevance weights with respect to the user query. The proposed approach is assessed using an image collection from the Corel database.
10 May 2025 in Sensors
Verified
Journal Article
Open access
PDF file
NANada Alzahrani
Nada Alzahrani
OBOuiem Bchir
Ouiem Bchir
MIMohamed Maher Ben Ismail
Mohamed Maher Ben Ismail
Automated action recognition has become essential in the surveillance, healthcare, and multimedia retrieval industries owing to the rapid proliferation of video data. This paper introduces YOLO-Act, a novel spatiotemporal action detection model that enhances the object detection capabilities of YOLOv8 to efficiently manage complex action dynamics within video sequences. YOLO-Act achieves precise and efficient action recognition by integrating keyframe extraction, action tracking, and class fusion. The model depicts essential temporal dynamics without the computational overhead of continuous frame processing by leveraging the adaptive selection of three keyframes representing the beginning, middle, and end of the actions. Compared with state-of-the-art approaches such as the Lagrangian Action Recognition Transformer (LART), YOLO-Act exhibits superior performance with a mean average precision (mAP) of 73.28 in experiments conducted on the AVA dataset, resulting in a gain of +28.18 mAP. Furthermore, YOLO-Act achieves this higher accuracy with significantly lower FLOPs, demonstrating its efficiency in computational resource utilization. The results highlight the advantages of incorporating precise tracking, effective spatial detection, and temporal consistency to address the challenges associated with video-based action detection.
19 April 2025 in Sensors
Verified
Journal Article
Open access
PDF file
AAAtheer Abdullah Alshahrani
Atheer Abdullah Alshahrani
OBOuiem Bchir
Ouiem Bchir
MIMohamed Maher Ben Ismail
Mohamed Maher Ben Ismail
Hyperspectral unmixing plays a fundamental role in mining meaningful information from hyperspectral data. It promotes advancements in various scientific, environmental, and industrial applications by extracting meaningful information from hyperspectral data. However, it is still hindered by several challenges, including accurately identifying the number of endmembers in a hyperspectral image, extracting the endmembers, and estimating their abundance fractions. This research addresses these challenges by employing a convolutional-neural-network-based autoencoder that leverages both the spatial and spectral information present in the hyperspectral image. Additionally, a self-learning module utilizing a fuzzy clustering algorithm is designed to determine the number of endmembers. A novel approach is also introduced that estimates the abundances of the endmembers from the autoencoder and the clustering output. Real datasets and relevant performance metrics were used to validate and evaluate the performance of the proposed method. The results demonstrate that our approach outperforms related methods, achieving improvements of 47% in Spectral Angle Distance (SAD) and 42% in root-mean-square error (RMSE).
28 December 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AAArwa Alturki
Arwa Alturki
OBOuiem Bchir
Ouiem Bchir
MIMohamed Maher Ben Ismail
Mohamed Maher Ben Ismail
In this paper, we propose two novel Adaptive Neural Network Approaches (ANNAs), which are intended to automatically learn the optimal network depth. In particular, the proposed class-independent and class-dependent ANNAs address two main challenges faced by typical deep learning paradigms. Namely, they overcome the problems of setting the optimal network depth and improving the model interpretability. Specifically, ANNA approaches simultaneously train the network model, learn the network depth in an unsupervised manner, and assign fuzzy relevance weights to each network layer to better decipher the model behavior. In addition, two novel cost functions were designed in order to optimize the layer fuzzy relevance weights along with the model hyper-parameters. The proposed ANNA approaches were assessed using standard benchmarking datasets and performance measures. The experiments proved their effectiveness compared to typical deep learning approaches, which rely on empirical tuning and scaling of the network depth. Moreover, the experimental findings demonstrated the ability of the proposed class-independent and class-dependent ANNAs to decrease the network complexity and build lightweight models for less overfitting risk and better generalization.
5 October 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
SASarah Fahad Alfayez
Sarah Fahad Alfayez
OBOuiem Bchir
Ouiem Bchir
MIMohamed Maher Ben Ismail
Mohamed Maher Ben Ismail
The effectiveness of deep learning models depends on their architecture and topology. Thus, it is essential to determine the optimal depth of the network. In this paper, we propose a novel approach to learn the optimal depth of a stacked AutoEncoder, called Dynamic Depth for Stacked AutoEncoders (DDSAE). DDSAE learns in an unsupervised manner the depth of a stacked AutoEncoder while training the network model. Specifically, we propose a novel objective function, aside from the AutoEncoder’s loss function to optimize the network depth: The optimization of the objective function determines the layers’ relevance weights. Additionally, we propose an algorithm that iteratively prunes the irrelevant layers based on the learned relevance weights. The performance of DDSAE was assessed using benchmark and real datasets.