Heterogeneous face recognition (HFR) aims to match face images across different imaging domains such as visible-to-infrared and visible-to-thermal. Recently, the increasing utility of nonvisible imaging has increased the application prospects of HFR in areas such as biometrics, security, and surveillance. HFR is a challenging variate of face recognition due to the differences between different imaging domains. While the current research has proposed image preprocessing, feature extraction, or common subspace projection for HFR, the optimization of these multi-stage methods is a challenging task as each step needs to be optimized separately and the performance error accumulates over each stage. In this paper, we propose a unified end-to-end Cross-Modality Discriminator Network (CMDN) for HFR. The proposed network uses a Deep Relational Discriminator module to learn deep feature relations for cross-domain face matching. Simultaneously, the CMDN is used to extract modality-independent embedding vectors for face images. The CMDN parameters are optimized using a novel Unit-Class Loss that shows higher stability and accuracy over other popular metric-learning loss functions. The experimental results on five popular HFR datasets demonstrate that the proposed method achieves significant improvement over the existing state-of-the-art methods.

Scene recognition is considered a challenging task of image recognition, mainly due to the presence of multiscale information of global layout and local objects in a given scene. Recent convolutional neural networks (CNNs) that can learn multiscale features have achieved remarkable progress in scene recognition. They have two limitations: 1) the receptive field (RF) size is fixed even though a scene may have large-scale variations and 2) they are computing and memory intensive, partially due to the representation of multiscales. To address these limitations, we propose a lightweight dynamic scene recognition approach based on a novel architectural unit, namely, a dynamic parallel pyramid (DPP) block, that can adaptively select RF size based on multiscale information from the input regarding channel dimensions. We encode multiscale features by applying different convolutional (CONV) kernels on different input tensor channels and then dynamically merge their output using a group attention mechanism followed by channel shuffling to generate the parallel feature pyramid. DPP can be easily incorporated with existing CNNs to develop new deep models, called DPP networks (DPP-Nets). Extensive experiments on large-scale scene image datasets, Places365 standard, Places365 challenge, the Massachusetts Institute of Technology (MIT) Indoor67, and Sun397 confirmed that the proposed method provides significant performance improvement compared with current state-of-the-art (SOTA) approaches. We also verified general applicability from compelling results on lightweight models of MobileNetV2 and ShuffleNetV2 on ImageNet-1k and small object centralized benchmarks on CIFAR-10 and CIFAR-100.

Applications for facial recognition have eased the process of personal identification. However, there are increasing concerns about the performance of these systems against the challenges of presentation attacks, spoofing, and disguises. One of the reasons for the lack of a robustness of facial recognition algorithms in these challenges is the limited amount of suitable training data. This lack of training data can be addressed by creating a database with the subjects having several disguises, but this is an expensive process. Another approach is to use generative adversarial networks to synthesize facial images with the required disguise add-ons. In this paper, we present a synthetic disguised face database for the training and evaluation of robust facial recognition algorithms. Furthermore, we present a methodology for generating synthetic facial images for the desired disguise add-ons. Cycle-consistency loss is used to generate facial images with disguises, e.g., fake beards, makeup, and glasses, from normal face images. Additionally, an automated filtering scheme is presented for automated data filtering from the synthesized faces. Finally, facial recognition experiments are performed on the proposed synthetic data to show the efficacy of the proposed methodology and the presented database. Training on the proposed database achieves an improvement in the rank-1 recognition rate (68.3%), over a model trained on the original nondisguised face images.

This paper provides a minimum time algorithm to intercept an object on the conveyor belt by robotic manipulator. The goal is that the robot is able to intercept objects on a conveyor line moving at a given speed in minimum time. In order to formulate the problem, we introduce the robot and object arrival time functions, and conclude that the optimal point occurs at the intersection of these two functions. The search algorithm for finding the intersection point between the robot and object arrival time functions are also presented to find the optimal point in real-time.

With the rapid development of the Internet and the mobile service robot, the digital services are becoming important factors for robots to recognize things in the real world. Advances in computer technology and the risk of copyright infringement have increased in the way that anyone replicates and copies digital media easily. Therefore, ways to prevent and suppress copyright infringement, digital watermarking technologies that insert copyrights information into the work, are being researched. Digital watermark, depending on the actual insert domain, can be categorized into the spatial domain and transform domain. In this paper, we propose an extended DCT domain watermarking for robot vision. The suggested method is by distributing and duplicating watermark images that are including copyright information on the original images. By doing this, it can be strong on geometric image attacks such as partial cutting, resizing, rotating, and so forth. For the success of watermark extraction, invertible process can be used to recover a disfigured image. Experimental results are provided to support these methods, through the process of recombination by complete image pieces.