With the development of large data age, Convolutional neural networks (CNNs) with more hidden layers have more complex network structure and more powerful feature learning and feature expression abilities than traditional machine learning methods. The convolution neural network model trained by the deep learning algorithm has made remarkable achievements in many large-scale identification tasks in the field of computer vision since its introduction. This paper first introduces the rise and development of deep learning and convolution neural network, and summarizes the basic model structure, convolution feature extraction and pooling operation of convolution neural network. Then, the research status and development trend of convolution neural network model based on deep learning in image classification are reviewed, which is mainly introduced from the aspects of typical network structure construction, training method and performance. Finally, some problems in the current research are briefly summarized and discussed, and the new direction of future development is forecasted.

Several deep image-based models which depend on deep learning have shown great success in the recorded computational and reconstruction efficiencies, especially for single high-resolution images. In the past, the use of super-resolution was commonly characterized by interference, and hence, the need for a model with higher performance. This study proposed a method for low to super-resolution face recognition, called efficient sub-pixel convolution neural network. This is a convolutional neural network which is usually employed at the time of image pre-processing to increase the chances of recognizing images with low resolution. The proposed Efficient Sub-Pixel Convolutional Neural Network is used for the conversion of low-resolution images into a high-resolution format for onward recognition. This conversion is based on the features extracted from the image. Using several evaluation tools, the proposed Efficient Sub-Pixel Convolutional Neural Network recorded a higher performance in terms of image resolution when compared to the performance of the benchmarked traditional methods. The evaluations were carried out on a Yale face database and ORL dataset faces. For Yale and ORL datasets, the obtained accuracy of the proposed method was 95.3% and 93.5%, respectively, which were higher than those of the other related methods.

In order to formalize information and knowledge about people, devices, applications, and services in the network system, this study provided a model for display

Face recognition from an image/video has been a fast-growing area in research community, and a sizeable number of face recognition techniques based on texture analysis have been developed in the past few years. Further, these techniques work well on gray-scale and colored images, but very few techniques deal with binary and low-resolution images. As the binary image is becoming the preferred format for low face resolution analysis, there is a need for further studies to provide a complete solution for the image-based face recognition system with a higher accuracy rate. To overcome the limitation of the existing methods in extracting distinctive features in low-resolution images due to the contrast between the face and background, we propose a statistical feature analysis technique to fill the gaps. To achieve this, the proposed technique integrates the binary-level occurrence matrix (BLCM) and the fuzzy local binary pattern (FLBP) named FBLCM to extract global and local features of the face from binary and low-resolution images. The purpose of FBLCM is to distinctively improve performance of edge sharpness between black and white pixels in the binary image and to extract significant data relating to the features of the face pattern. Experimental results on Yale and FEI datasets validate the superiority of the proposed technique over the other top-performing feature analysis methods. The developed technique has achieved the accuracy of 94.54% when a random forest classifier is used, hence outperforming other techniques such as the gray-level co-occurrence matrix (GLCM), bag of word (BOW), and fuzzy local binary pattern (FLBP), respectively.

Invariant descriptor for shape and texture image recognition usage is an essential branch of pattern recognition. It is made up of techniques that aim at extracting information from shape images via human knowledge and works. The descriptors need to have strong Local Binary Pattern (LBP) in order to encode the information distinguishing them. Local Binary Pattern (LBP) ensures encoding global and local information and scaling invariance by introducing a look-up table to reflect the uniformity structure of an object. It is needed as the edge direction matrices (EDMS) only apply global invariant descriptor which employs first and secondary order relationships. The main objective of this paper is the need of improved recognition capabilities which achieved by the combining LBP and EDMS. Working together, these two descriptors will add advantages to the program and enable the researcher to investigate the weaknesses of each one. Two classifiers are used: multi-layer neural network and random forest. The techniques used in this paper are compared with Gray-Level Co-occurrence matrices (GLCM-EDMS) and Scale Invariant Feature Transform (SIFT) by using two benchmark dataset: MPEG-7 CE-Shape-1 for shape and Arabic calligraphy for texture. The experiments have shown the superiority of the introduced descriptor over the GLCM-EDMS and the SIFT.

Shapes and texture image recognition usage is an essential branch of pattern recognition. It is made up of techniques that aim at extracting information from images via human knowledge and works. Local Binary Pattern (LBP) ensures encoding global and local information and scaling invariance by introducing a look-up table to reflect the uniformity structure of an object. However, edge direction matrixes (EDMS) only apply global invariant descriptor which employs first and secondary order relationships. The main idea behind this methodology is the need of improved recognition capabilities, a goal achieved by the combinative use of these descriptors. This collaboration aims to make use of the major advantages each one presents, by simultaneously complementing each other, in order to elevate their weak points. By using multiple classifier approaches such as random forest and multi-layer perceptron neural network, the proposed combinative descriptor are compared with the state of the art combinative methods based on Gray-Level Co-occurrence matrix (GLCM with EDMS), LBP and moment invariant on four benchmark dataset MPEG-7 CE-Shape-1, KTH-TIPS image, Enghlishfnt and Arabic calligraphy . The experiments have shown the superiority of the introduced descriptor over the GLCM with EDMS, LBP and moment invariants and other well-known descriptor such as Scale Invariant Feature Transform from the literature.