Anti-packing Pattern Representation Model Research Articles

A Novel Semantic Segmentation Algorithm for RGB-D Images Based on Non-Symmetry and Anti-Packing Pattern Representation Model

With the rapid development of deep learning technology, the accuracy of image semantic segmentation tasks has been greatly improved. However, indoor RGB-D semantic segmentation remains a challenging problem because of the complexity of indoor environments. The emergence of depth sensors makes depth information gradually used to improve the effect of semantic segmentation. The splicing of weights such as between the RGB features and the depth features which are used as the input features of the neural network can effectively improve the accuracy of the indoor semantic segmentation tasks. Most previous researches focused on improving the performance of semantic segmentation by adjusting the structure of convolutional neural network. These researches have either added attention mechanism or performed data augmentation on input features, but they didn’t make full use of the boundary information and the texture information of the original RGB image. In this paper, we propose a semantic segmentation algorithm for RGB-D images based on Non-symmetry and Anti-packing pattern representation Model (NAM). The core idea of the proposed algorithm is to take the channel-wise concatenation of pre-segmentation labels provided by the traditional hierarchical image segmentation and RGB-D features as the input of the neural network so as to guide the semantic segmentation tasks. The extensive experiments are conducted on the popular indoor RGB-D semantic segmentation datasets. When compared with the state-of-art algorithms, the experimental results presented in this paper show that our proposed method has improved the performance of image semantic segmentation networks on several popular neural network architectures.

Hierarchical Image Segmentation Based on Nonsymmetry and Anti-Packing Pattern Representation Model.

Image segmentation is the foundation of high-level image analysis and image understanding. How to effectively segment an image into regions that are "meaningful" to the human visual perception and ensure that the segmented regions are consistent at different resolutions is still a very challenging issue. Inspired by the idea of the Nonsymmetry and Anti-packing pattern representation Model in the Lab color space (NAMLab) and the "global-first" invariant perceptual theory, in this paper, we propose a novel framework for hierarchical image segmentation. Firstly, by defining the dissimilarity between two pixels in the Lab color space, we propose an NAMLab-based color image representation approach that is more in line with the human visual perception characteristics and can make the image pixels fast and effectively merge into the NAMLab blocks. Then, by defining the dissimilarity between two NAMLab-based regions and iteratively executing NAMLab-based merging algorithm of adjacent regions into larger ones to progressively generate a segmentation dendrogram, we propose a fast NAMLab-based algorithm for hierarchical image segmentation. Finally, the complexities of our proposed NAMLab-based algorithm for hierarchical image segmentation are analyzed in details. The experimental results presented in this paper show that our proposed algorithm when compared with the state-of-the-art algorithms not only can preserve more details of the object boundaries, but also it can better identify the foreground objects with similar color distributions. Also, our proposed algorithm can be executed much faster and takes up less memory and therefore it is a better algorithm for hierarchical image segmentation.

A Novel Pencil Drawing Algorithm Based on Non-Symmetry and Anti-Packing Pattern Representation Model

The artistic stylization transformation of images is an important part in the research of Non-Photorealistic Rendering (NPR). This kind of non-realistic stylized research has a very strong realistic romantic temperament and it can express the artistic pursuit of researchers very well. It is a good example of practical application combining computer science and art. In the technology of image style conversion, the simulation of the realistic art style includes mainly cartoon style, oil painting style, ink painting style and pencil drawing style. Previously, some researchers proposed a style conversion method based on the prior knowledge that there might be crosses at the junction of two lines where the tone distribution has a certain rule. However, in this paper, we have focused on the use of an edge extraction algorithm based on Non-symmetry and Anti-packing pattern representation Model (NAM) to enhance the pencil strokes and highlight the details of the image. Then, by combining the line pencil strokes with the tone drawing, we can transform the image into an image with pencil sketch style. Finally, compared with the most important previous methods, the experimental results presented in this paper showed that our proposed method showed more clearly the scene and the content and more details of the image than the previous methods. We also verified our method and calculated Structural Similarity (SSIM) and Peak Signal-to-Noise Ratio (PSNR) of original images and color pencil drawings with different algorithms on the 7 nature images and the BSDS500 data set.

Application of RNAMlet to surface defect identification of steels

As three main production lines of steels, continuous casting slabs, hot rolled steel plates and cold rolled steel strips have different surface appearances and are produced at different speeds of their production lines. Therefore, the algorithms for the surface defect identifications of the three steel products have different requirements for real-time and anti-interference. The existing algorithms cannot be adaptively applied to surface defect identification of the three steel products. A new method of adaptive multi-scale geometric analysis named RNAMlet was proposed. The idea of RNAMlet came from the non-symmetry anti-packing pattern representation model (NAM). The image is decomposed into a set of rectangular blocks asymmetrically according to gray value changes of image pixels. Then two-dimensional Haar wavelet transform is applied to all blocks. If the image background is complex, the number of blocks is large, and more details of the image are utilized. If the image background is simple, the number of blocks is small, and less computation time is needed. RNAMlet was tested with image samples of the three steel products, and compared with three classical methods of multi-scale geometric analysis, including Contourlet, Shearlet and Tetrolet. For the image samples with complicated backgrounds, such as continuous casting slabs and hot rolled steel plates, the defect identification rate obtained by RNAMlet was 1% higher than other three methods. For the image samples with simple backgrounds, such as cold rolled steel strips, the computation time of RNAMlet was one-tenth of the other three MGA methods, while the defect identification rates obtained by RNAMlet were higher than the other three methods.

Using Non-symmetry and Anti-packing Representation Model for Object Detection

In this paper, we present a non-symmetry and anti-packing object pattern representation model (NAM) for object detection. A set of distinctive sub-patterns (object parts) is constructed from a set of sample images of the object class; object pattern are then represented using sub-patterns, together with spatial relations observed among the sub-patterns. Many feature descriptors can be used to describe these sub-patterns. he NAM model codes the global geometry of object category, and the local feature descriptor of sub-patterns deal with the local variation of object. By using Edge Direction Histogram (EDH) features to describe local sub-pattern contour shape within an image, we found that richer shape information is helpful in improving recognition performance. Based on this representation, several learning classifiers are used to detect instances of the object class in a new image. The experimental results on a variety of categories demonstrate that our approach provides successful detection of the object within the image.

A new fast edge detection algorithm based on NAM-structured plane decomposition

The nonsymmetry and antipacking pattern representation model (NAM), inspired by the concept of the packing problem, uses a set of subpatterns to represent an original pattern. The NAM is a promising method for image representation because of its ability to focus on the interesting subsets of an image. In this paper, we develop a new method for gray-scale image representation based on NAM, called NAM-structured plane decomposition (NAMPD), in which each subpattern is associated with a rectangular region in the image. The luminance function of pixels in this region is approximated by an oblique plane model. Then, we propose a new and fast edge detection algorithm based on NAMPD. The theoretical analyses and experimental results presented in this paper show that the edge detection algorithm using NAMPD performs faster than the classical ones because it permits the execution of operations on subpatterns instead of pixels.

A Color Image Representation Method Based on Non-Symmetry and Anti-Packing Model

With the concept of the packing problem,this paper presents a color image representation method based on the non-symmetry and anti-packing pattern representation model(NAM).By describing the NAM and the method of the binary-bit plane decomposition(BPD)for the color image,a novel NAM-based representation algorithm for the color image is proposed.Also,the total data amount of the algorithm is analyzed.The theoretical and experimental results presented in this paper show that the NAM-based representation method can reduce the data storage much more effectively than the hierarchical structural linear quadtree-based representation method and is a better method to represent the color image pattern.The method is a new research area with respect to the color pattern representation and is valuable for the theoretical research and potential practical values such as decreasing the storage room,increasing the transmission speed,quickening the process procedure,matching pattern,and so on.