Research on a Convolution Kernel Initialization Method for Speeding Up the Convergence of CNN

This paper presents a convolution kernel initialization method based on the local binary patterns (LBP) algorithm and sparse autoencoder. This method can be applied to the initialization of the convolution kernel in the convolutional neural network (CNN). The main function of the convolution kernel is to extract the local pattern of the image by template matching as the target feature of subsequent image recognition. In general, the Xavier initialization method and the He initialization method are used to initialize the convolution kernel. In this paper, firstly, some typical sample images were selected from the training set, and the LBP algorithm was applied to extract the texture information of the typical sample images. Then, the texture information was divided into several small blocks, and these blocks were input into the sparse autoencoder (SAE) for pre-training. After finishing the training, the weight values of the sparse autoencoder that met the statistical features of the data set were used as the initial value of the convolution kernel in the CNN. The experimental result indicates that the method proposed in this paper can speed up the convergence of the network in the network training process and improve the recognition rate of the network to an extent.

Fast Segmentation of Vertebrae CT Image Based on the SNIC Algorithm

Automatic image segmentation plays an important role in the fields of medical image processing so that these fields constantly put forward higher requirements for the accuracy and speed of segmentation. In order to improve the speed and performance of the segmentation algorithm of medical images, we propose a medical image segmentation algorithm based on simple non-iterative clustering (SNIC). Firstly, obtain the feature map of the image by extracting the texture information of it with feature extraction algorithm; Secondly, reduce the image to a quarter of the original image size by downscaling; Then, the SNIC super-pixel algorithm with texture information and adaptive parameters which used to segment the downscaling image to obtain the superpixel mark map; Finally, restore the superpixel labeled image to the original size through the idea of the nearest neighbor algorithm. Experimental results show that the algorithm uses an improved superpixel segmentation method on downscaling images, which can increase the segmentation speed when segmenting medical images, while ensuring excellent segmentation accuracy.

Robot-Based Creation of Complete 3D Workpiece Models

A complete object database containing a model (representing geometric and texture information) of every possible workpiece is a common necessity e.g. for different object recognition or task planning approaches. The generation of these models is often a tedious process. In this paper we present a fully automated approach to tackle this problem by generating complete workpiece models using a robotic manipulator. A workpiece is recorded by a depth sensor from multiple views for one side, then turned, and captured from the other side. The resulting point clouds are merged into one complete model. Additionally, we represent the information provided by the object’s texture using keypoints. We present a proof of concept and evaluate the precision of the final models. In the end we conclude the usefulness of our approach showing a precision of around 1 mm for the resulting models.

Multi-Channel Local Binary Pattern Guided Convolutional Neural Network for Breast Cancer Classification

Background: The advancement in convolutional neural network (CNN) has reduced the burden of experts using the computer-aided diagnosis of human breast cancer. However, most CNN networks use spatial features only. The inherent texture structure present in histopathological images plays an important role in distinguishing malignant tissues. This paper proposes an alternate CNN network that integrates Local Binary Pattern (LBP) based texture information with CNN features. Methods: The study propagates that LBP provides the most robust rotation, and translation-invariant features in comparison with other texture feature extractors. Therefore, a formulation of LBP in context of convolution operation is presented and used in the proposed CNN network. A non-trainable fixed set binary convolutional filters representing LBP features are combined with trainable convolution filters to approximate the response of the convolution layer. A CNN architecture guided by LBP features is used to classify the histopathological images. Result: The network is trained using BreKHis datasets. The use of a fixed set of LBP filters reduces the burden of CNN by minimizing training parameters by a factor of 9. This makes it suitable for the environment with fewer resources. The proposed network obtained 96.46% of maximum accuracy with 98.51% AUC and 97% F1-score. Conclusion: LBP based texture information plays a vital role in cancer image classification. A multi-channel LBP futures fusion is used in the CNN network. The experiment results propagate that the new structure of LBP-guided CNN requires fewer training parameters preserving the capability of the CNN network’s classification accuracy.

Automatic, Multiview, Coplanar Extraction for CityGML Building Model Texture Mapping

Most 3D CityGML building models in street-view maps (e.g., Google, Baidu) lack texture information, which is generally used to reconstruct real-scene 3D models by photogrammetric techniques, such as unmanned aerial vehicle (UAV) mapping. However, due to its simplified building model and inaccurate location information, the commonly used photogrammetric method using a single data source cannot satisfy the requirement of texture mapping for the CityGML building model. Furthermore, a single data source usually suffers from several problems, such as object occlusion. We proposed a novel approach to achieve CityGML building model texture mapping by multiview coplanar extraction from UAV remotely sensed or terrestrial images to alleviate these problems. We utilized a deep convolutional neural network to filter out object occlusion (e.g., pedestrians, vehicles, and trees) and obtain building-texture distribution. Point-line-based features are extracted to characterize multiview coplanar textures in 2D space under the constraint of a homography matrix, and geometric topology is subsequently conducted to optimize the boundary of textures by using a strategy combining Hough-transform and iterative least-squares methods. Experimental results show that the proposed approach enables texture mapping for building façades to use 2D terrestrial images without the requirement of exterior orientation information; that is, different from the photogrammetric method, a collinear equation is not an essential part to capture texture information. In addition, the proposed approach can significantly eliminate blurred and distorted textures of building models, so it is suitable for automatic and rapid texture updates.

INF-GAN: Generative Adversarial Network for Illumination Normalization of Finger-Vein Images

When images are acquired for finger-vein recognition, images with nonuniformity of illumination are often acquired due to varying thickness of fingers or nonuniformity of illumination intensity elements. Accordingly, the recognition performance is significantly reduced as the features being recognized are deformed. To address this issue, previous studies have used image preprocessing methods, such as grayscale normalization or score-level fusion methods for multiple recognition models, which may improve performance in images with a low degree of nonuniformity of illumination. However, the performance cannot be improved drastically when certain parts of images are saturated due to a severe degree of nonuniformity of illumination. To overcome these drawbacks, this study newly proposes a generative adversarial network for the illumination normalization of finger-vein images (INF-GAN). In the INF-GAN, a one-channel image containing texture information is generated through a residual image generation block, and finger-vein texture information deformed by the severe nonuniformity of illumination is restored, thus improving the recognition performance. The proposed method using the INF-GAN exhibited a better performance compared with state-of-the-art methods when the experiment was conducted using two open databases, the Hong Kong Polytechnic University finger-image database version 1, and the Shandong University homologous multimodal traits finger-vein database.

MR-InpaintNet: Toward Deep Multi-Resolution Learning for Progressive Image Inpainting

<div>Deep learning based image inpainting methods have improved the performance greatly due to powerful representation ability of deep learning. However, current deep inpainting methods still tend to produce unreasonable structure and blurry texture, implying that image inpainting is still a challenging topic due to the ill-posed property of the task. To address these issues, we propose a novel deep multi-resolution learning-based progressive image inpainting method, termed MR-InpaintNet, which takes the damaged images of different resolutions as input and then fuses the multi-resolution features for repairing the damaged images. The idea is motivated by the fact that images of different resolutions can provide different levels of feature information. Specifically, the low-resolution image provides strong semantic information and the high-resolution image offers detailed texture information. The middle-resolution image can be used to reduce the gap between low-resolution and high-resolution images, which can further refine the inpainting result. To fuse and improve the multi-resolution features, a novel multi-resolution feature learning (MRFL) process is designed, which is consisted of a multi-resolution feature fusion (MRFF) module, an adaptive feature enhancement (AFE) module and a memory enhanced mechanism (MEM) module for information preservation. Then, the refined multi-resolution features contain both rich semantic information and detailed texture information from multiple resolutions. We further handle the refined multiresolution features by the decoder to obtain the recovered image. Extensive experiments on the Paris Street View, Places2 and CelebA-HQ datasets demonstrate that our proposed MRInpaintNet can effectively recover the textures and structures, and performs favorably against state-of-the-art methods.</div>

MR-InpaintNet: Toward Deep Multi-Resolution Learning for Progressive Image Inpainting

<div>Deep learning based image inpainting methods have improved the performance greatly due to powerful representation ability of deep learning. However, current deep inpainting methods still tend to produce unreasonable structure and blurry texture, implying that image inpainting is still a challenging topic due to the ill-posed property of the task. To address these issues, we propose a novel deep multi-resolution learning-based progressive image inpainting method, termed MR-InpaintNet, which takes the damaged images of different resolutions as input and then fuses the multi-resolution features for repairing the damaged images. The idea is motivated by the fact that images of different resolutions can provide different levels of feature information. Specifically, the low-resolution image provides strong semantic information and the high-resolution image offers detailed texture information. The middle-resolution image can be used to reduce the gap between low-resolution and high-resolution images, which can further refine the inpainting result. To fuse and improve the multi-resolution features, a novel multi-resolution feature learning (MRFL) process is designed, which is consisted of a multi-resolution feature fusion (MRFF) module, an adaptive feature enhancement (AFE) module and a memory enhanced mechanism (MEM) module for information preservation. Then, the refined multi-resolution features contain both rich semantic information and detailed texture information from multiple resolutions. We further handle the refined multiresolution features by the decoder to obtain the recovered image. Extensive experiments on the Paris Street View, Places2 and CelebA-HQ datasets demonstrate that our proposed MRInpaintNet can effectively recover the textures and structures, and performs favorably against state-of-the-art methods.</div>