With the development of 3-D applications, such as 3-D reconstruction and object recognition, accurate and high-quality depth map is urgently required. Recently, depth cameras have been affordable and widely used in daily life. However, the captured depth map always owns low resolution and poor quality, which limits its practical application. This paper proposes a color-guided depth map super resolution method using convolutional neural network. First, a dual-stream convolutional neural network, which integrates the color and depth information simultaneously, is proposed for depth map super resolution. Then, the optimized edge map generated by the high resolution color image and low resolution depth map is used as additional information to refine the object boundary in the depth map. Experimental results demonstrate the effectiveness of the proposed method compared with the state-of-the-art methods.

Color-Guided Depth Map Super Resolution Using Convolutional Neural Network

As stored data and images on memory disks increase, image retrieval has a necessary task on image processing. Although lots of researches have been reported for this task so far, semantic gap between low level features of images and human concept is still an important challenge on content-based image retrieval. For this task, a robust method is proposed by a combination of convolutional neural network and sparse representation, in which deep features are extracted by using CNN and sparse representation to increase retrieval speed and accuracy. The proposed method has been tested on three common databases on image retrieval, named Corel, ALOI and MPEG7. By computing metrics such as P(0.5), P(1) and ANMRR, experimental results show that the proposed method has achieved higher accuracy and better speed compared to state-of-the-art methods.

Content-based image retrieval by combining convolutional neural networks and sparse representation

For the problems of missing edges and obvious artifacts in Electrical Capacitance Tomography (ECT) reconstruction algorithms, an image reconstruction method based on a multiscale dual-channel convolutional neural network is proposed. Firstly, the image reconstructed by Landweber algorithm is input into the convolutional neural network, and four scales are selected for feature extraction. Feature unions are used across the scales to fuse the information of the output layer with feature maps. To improve the imaging accuracy, two frequency channels are designed for the input image. The middle layer of the network consists of two fully convolutional structures. Convolutional layers and jump connections are designed separately for different channels, which greatly improves the network’s ability to extract feature information and reduces the number of feature maps required for each layer. The number of network layers is shallow, which can speed up the network training, prevent the network from falling into local optimum, and ensure the effective transmission of image details. Simulation experiments are carried out for four typical dual media distributions. The edges of the reconstructed image are smoother and the image error is smaller. It effectively resolves the lack of edges in the reconstruction image and reduces the image edge artifacts in the ECT system.

/pdf/ect-image-reconstruction-algorithm-based-on-multiscale-dual-3h9iyqnt74.pdf

ECT Image Reconstruction Algorithm Based on Multiscale Dual-Channel Convolutional Neural Network

In recent years, the deep hashing image retrieval algorithm has become a hot spot in current research. Although the deep hashing algorithm has achieved good results in image retrieval, how to further improve the accuracy of the image retrieval algorithm and reduce the computational complexity of the algorithm, the two basic requirements of the algorithm, need attention in image retrieval. The paper proposes a new Aggregate Deep Fast Supervised Discrete Hashing (ADFSDH) method for highly efficient image retrieval on large-scale datasets. Specifically, in order to improve the algorithm performance, the paper first proposes a new Aggregate Deep Convolutional Neural Network (ADCNN) mode based on VGG16, VGG19 and transfer learning for effective image feature extraction, which contains two different feature extractors in parallel. And then, the paper proposes a new feature fusion method. When our weighted proportion is consistent with the Mean Average Precision results of two different feature extractors, we can obtain the most accurate description of the image. Firstly, in order to save ADCNN required storage space and improve ADCNN image retrieval efficiency, the Fast Supervised Discrete Hashing algorithm after adjusting the parameters is introduced into the ADCNN model. In addition, ADFSDH unifies feature learning and hash coding into the same framework. The proposed method was experimented on three datasets (CIFAR10, MNIST and FD-XJ), and the result shows that it is superior to the current mainstream approaches in image retrieval.

A novel deep hashing method for fast image retrieval

Convolutional neural networks (CNN) have turned into one of the key algorithms in machine learning for content classification of digital images. Nevertheless, the CNN computational complexity is considerable larger than classic algorithms, thus, CPU- or GPU-based platforms are generally used for CNN implementations in many applications, but often do not fulfill portable requirements due to resources, energy and real-time constrains. Therefore, there is a growing interest on real time processing solutions for object recognition using CNNs mainly implemented on embedded systems, which are limited both in resources and energy consumption. An updated review of prominent reported approaches for mapping CNNs onto embedded systems is described in this paper. Two main solutions trends for reducing the hardware CNN workload are distinguished through a deduced taxonomy. One is focused on algorithm level solutions to reduce the number of multiplications and CNN coefficients. On the other hand, hardware level solutions goal is to achieve processing time, power consumption and hardware resources reduction. Two dominant hardware level design strategies are pointed out as oriented to either reducing the energy consumption and resources utilization meeting real-time requirements or increasing the throughput at the expense of resources utilization. Finally, two identified design strategies for CNN hardware accelerators are proposed as opportunity research areas.

Review of prominent strategies for mapping CNNs onto embedded systems

With the increasing amount of image data, the image retrieval methods have several drawbacks, such as the low expression ability of visual feature, high dimension of feature, low precision of image retrieval and so on To solve these problems, a learning method of binary hashing based on deep convolutional neural networks is proposed The basic idea is to add a hash layer into the deep learning framework and simultaneously learn image features and hash functions which should satisfy independence and quantization error minimized First, convolutional neural network is employed to learn the intrinsic implications of training images so as to improve the distinguish ability and expression ability of visual feature Second, the visual feature is putted into the hash layer, in which hash functions are learned And the learned hash functions should satisfy the classification error and quantization error minimized and the independence constraint Finally, given an input image, hash codes are generated by the output of the hash layer of the proposed framework and large scale image retrieval can be accomplished in low-dimensional hamming space Experimental results on the three benchmark datasets show that the binary hash codes generated by the proposed method has superior performance gains over other state-of-the-art hashing methods

Tian-qiang Peng

Papers

Image retrieval based on deep Convolutional Neural Networks and binary hashing learning