Face recognition has received significant attention because of its numerous applications in access control, law enforcement, security, surveillance, Internet communication and computer entertainment. Although significant progress has been made, the state‐of‐the‐art face recognition systems yield satisfactory performance only under controlled scenarios and they degrade significantly when confronted with real‐world scenarios. The real‐world scenarios have unconstrained conditions such as illumination and pose variations, occlusion and expressions. Thus, there remain plenty of challenges and opportunities ahead. Latterly, some researchers have begun to examine face recognition under unconstrained conditions. Instead of providing a detailed experimental evaluation, which has been already presented in the referenced works, this study serves more as a guide for readers. Thus, the goal of this study is to discuss the significant challenges involved in the adaptation of existing face recognition algorithms to build successful systems that can be employed in the real world. Then, it discusses what has been achieved so far, focusing specifically on the most successful algorithms, and overviews the successes and failures of these algorithms to the subject. It also proposes several possible future directions for face recognition. Thus, it will be a good starting point for research projects on face recognition as useful techniques can be isolated and past errors can be avoided.

Sign language is the most natural and effective way for communications among deaf and normal people. American Sign Language (ASL) alphabet recognition (i.e. fingerspelling) using marker-less vision sensor is a challenging task due to the difficulties in hand segmentation and appearance variations among signers. Existing color-based sign language recognition systems suffer from many challenges such as complex background, hand segmentation, large inter-class and intra-class variations. In this paper, we propose a new user independent recognition system for American sign language alphabet using depth images captured from the low-cost Microsoft Kinect depth sensor. Exploiting depth information instead of color images overcomes many problems due to their robustness against illumination and background variations. Hand region can be segmented by applying a simple preprocessing algorithm over depth image. Feature learning using convolutional neural network architectures is applied instead of the classical hand-crafted feature extraction methods. Local features extracted from the segmented hand are effectively learned using a simple unsupervised Principal Component Analysis Network (PCANet) deep learning architecture. Two strategies of learning the PCANet model are proposed, namely to train a single PCANet model from samples of all users and to train a separate PCANet model for each user, respectively. The extracted features are then recognized using linear Support Vector Machine (SVM) classifier. The performance of the proposed method is evaluated using public dataset of real depth images captured from various users. Experimental results show that the performance of the proposed method outperforms state-of-the-art recognition accuracy using leave-one-out evaluation strategy.

Pixel value differencing (PVD) and least significant bit substitution (LSB) are two widely used schemes in image steganography. These two methods do not consider different content in a cover image for hiding the secret data. The content of most digital images has different edge directions in each pixel, and the local object shape or appearance is mostly characterized by the distribution of its intensity gradients or edge directions. Exploiting these characteristics for embedding various secret information in different edge directions will eliminate sequential embedding and improve robustness. Thus, a histogram of oriented gradient (HOG) algorithm is proposed to find the dominant edge direction for each 2 × 2 block of cover images. Blocks of interest (BOIs) are determined adaptively based on the gradient magnitude and angle of the cover image. Then, the PVD algorithm is used to hide secret data in the dominant edge direction, while the LSB substitution is utilized in the other two remaining pixels. Extensive experiments using various standard images reveal that the proposed scheme provides high embedding capacity and better visual quality compared with several other PVD- and LSB-based methods. Moreover, it resists various steganalysis techniques, such as pixel difference histogram and RS analysis.

Deep Convolutional Neural Networks (DCNN) are currently the predominant technique commonly used to learn visual features from images. However, the complex structure of most recent DCNNs impose two major requirements namely, huge labeled dataset and high computational resources. In this paper, we develop a new efficient deep unsupervised network to learn invariant image representation from unlabeled visual data. The proposed Deep Convolutional Self-organizing Maps (DCSOM) network comprises a cascade of convolutional SOM layers trained sequentially to represent multiple levels of features. The 2D SOM grid is commonly used for either data visualization or feature extraction. However, this work employs high dimensional map size to create a new deep network. The N-Dimensional SOM (ND-SOM) grid is trained to extract abstract visual features using its classical competitive learning algorithm. The topological order of the features learned from ND-SOM helps to absorb local transformation and deformation variations exhibited in the visual data. The input image is divided into an overlapped local patches where each local patch is represented by the N-coordinates of the winner neuron in the ND-SOM grid. Each dimension of the ND-SOM can be considered as a non-linear principal component and hence it can be exploited to represent the input image using N-Feature Index Image (FII) bank. Multiple convolutional SOM layers can be cascaded to create a deep network structure. The output layer of the DCSOM network computes local histograms of each FII bank in the final convolutional SOM layer. A set of experiments using MNIST handwritten digit database and all its variants are conducted to evaluate the robust representation of the proposed DCSOM network. Experimental results reveal that the performance of DCSOM outperforms state-of-the-art methods for noisy digits and achieve a comparable performance with other complex deep learning architecture for other image variations.