Evaluation of Scumming Printing Defect by Using Computer Vision-based Bit Plane Slicing Method

The generative adversarial network learns different kinds of real images and generates corresponding fake images. The image quality generated based on the generative adversarial network show the strength of the learning ability of the model for different kinds of images. Based on the apparent differences in features of different types of images, this paper proposes to judge the strength of features of different kinds of images in the generative adversarial network learning process based on generative adversarial networks and convolutional neural networks. The experiment uses three different kinds of data sets, including cartoon, face and food, and carries out three groups of experiments. The experimental results show that the simpler the image is, the stronger the learning ability is.

In this letter, we derive the theoretical complex cepstrum (TCC) of the discrete cosine transform (DCT) and warped DCT (WDCT) filters. Using these derivations, we intend to develop an analytic model of the warped discrete cosine transform cepstrum (WDCTC), which was recently introduced as a speech processing feature. In our derivation, we start with the filter bank structure for the DCT, where each basis is represented by a finite impulse response (FIR) filter. The WDCT filter bank is obtained by substituting z <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-1</sup> in the DCT filter bank with a first-order all-pass filter. Using the filter bank structures, we first derive the transfer functions for the DCT and WDCT, and subsequently, the TCC for each filter is computed. We analyze the DCT and WDCT filter transfer functions and the TCC by illustrating the corresponding pole-zero maps and cepstral sequences. Moreover, we also use the derived TCC expressions to compute the cepstral sequence for a synthetic vowel /aa/ where the observations on the theoretical cepstrum corroborate well with our practical findings

The harmonic neural network (HNN) learns a combination of discrete cosine transform (DCT) filters to obtain an integrated feature from all spectra in the frequency domain. HNN, however, faces two challenges in learning and inference processes. First, the spectrum feature learned by HNN is insufficient and limited because the number of DCT filters is much smaller than that of feature maps. In addition, the number of parameters and the computation costs of HNN are significantly high because the intermediate spectrum layers are expanded multiple times. These two challenges will severely harm the performance and efficiency of HNN. To solve these problems, we first propose the compound DCT (C-DCT) filters integrating the nearest DCT filters to retrieve rich spectrum features to improve the performance. To significantly reduce the model size and computation complexity for improving the efficiency, the shared reconstruction filter is then proposed to share and dynamically drop the meta-filters in every frequency branch. Integrating the C-DCT filters with the shared reconstruction filters, the efficient harmonic network (EH-Net) is introduced. Extensive experiments on different datasets demonstrate that the proposed EH-Nets can effectively reduce the model size and computation complexity while maintaining the model performance. The code has been released at https://github.com/zhangle408/EH-Nets.

Content Based Image Retrieval (CBIR) is an important and widely used technique for retrieval of different kinds of images from large database. Collection of information in database are available in different formats such as text, image, graph, chart etc. Here, our focus is on information which is available in the form of images. Searching and retrieval of the image from a large amount of database is difficult problem because it uses the image visual information such as shape, text and color for indexing and representation of an image. For efficient CBIR system, there is a need to develop different kinds of retrieval methods using feature extraction, similarity matching etc. Text Based Image Retrieval systems are used in many hospitals, but for large databases these are inefficient. To solve this problem, CBIR systems are proposed to retrieve matching images from database using automated feature extraction method. At present, medical imaging field finds extensive growth in the generation and evaluation of various types of medical images which are high inconsistency, usually fused and the combination of various minor composition structures. For easy retrieval, need to be development of feature extraction and image classification methods. Different methods are used for different kinds of medical images. The Radiology department and Cardiology department are the largest producers of medical images and the patient abnormal images can be stored with the normal images. CBIR uses query image as input and it retrieves the images, which are similar to the query more efficiently and effectively. This paper provides a comprehensive Survey about CBIR system and its one of the major application in medical domain.

Since pre-processing and initial segmentation steps in medical images directly affect the final segmentation results of the regions of interesting, an automatic segmentation method of a parameter-adaptive pulse-coupled neural network is proposed to integrate the above-mentioned two segmentation steps into one. This method has a low computational complexity for different kinds of medical images and has a high segmentation precision. The method comprises four steps. Firstly, an optimal histogram threshold is used to determine the parameter [Formula: see text] for different kinds of images. Secondly, we acquire the parameter [Formula: see text] according to a simplified pulse-coupled neural network (SPCNN). Thirdly, we redefine the parameter V of the SPCNN model by sub-intensity distribution range of firing pixels. Fourthly, we add an offset [Formula: see text] to improve initial segmentation precision. Compared with the state-of-the-art algorithms, the new method achieves a comparable performance by the experimental results from ultrasound images of the gallbladder and gallstones, magnetic resonance images of the left ventricle, and mammogram images of the left and the right breast, presenting the overall metric UM of 0.9845, CM of 0.8142, TM of 0.0726. The algorithm has a great potential to achieve the pre-processing and initial segmentation steps in various medical images. This is a premise for assisting physicians to detect and diagnose clinical cases.

In image denoising techniques, the state-of-the-art Discrete Cosine Transform (DCT) domain filters manifest good performance of reducing additive Gaussian white noise (AGWN). Two DCT domain filters, i.e., the block-matching three-dimensional (BM3D) DCT filter and the shape-adaptive (SA) DCT filter, have been investigated. However, these DCT domain filters introduce the temporal fluctuation artifact when denoising the noisy videos. In this paper, a robust statistical adaptive temporal (RSAT) filter is proposed to reduce the temporal fluctuation artifact. The parameters of the RSAT filter can be adaptively configured according to the local statistics of the adjacent video frames. In addition, the above DCT domain filters combined with a modified impulse filter are used to suppress the mixed Gaussian-and-impulse noise (MGIN). Experimental results show that the proposed algorithm markedly suppresses the annoying artifact, in terms of the peak signal-to-noise ratio (PSNR) as well as the visual quality.

The PCNN (pulse coupled neural network), an artificial neural network based on biology, can be efficiently applied to image segmentation. The performance of image segmentation based on PCNN depends on suitable PCNN parameters. However, it is difficult to get suitable PCNN parameters for different kinds of images because different kinds of images have different suitable PCNN parameters. So far, no paper has described how to get the suitable PCNN parameters to efficiently segment images. In this paper, we put forward a new approach for image segmentation based on a unit-linking PCNN, by which we can use the same PCNN parameter to efficiently segment different kinds of images. Therefore, using this new approach can automatically and efficiently segment images without choosing different parameters for different kinds of images.

This paper discusses a comparison of Finite Impulse response (FIR) and Discrete Cosine Transform (DCT) implementation on FPGA Xilinx Artix-7 FPGA. They are representative of time and frequency domain filter. The system involves audio codec interface to verify the frequency response. The number of tap is varied from 64, 128 and 256 with 600, 700 and 800 Hz cut off frequencies. The low pass filter coefficients are generated from Matlab, then implemented in FPGA using Hanning window and 48kHz frequency sampling. Hardware level verification and implementation show that DCT filter requires higher resources than FIR filter. However, the timing report expresses that the DCT filter has shorter critical path than FIR filter. Moreover, based on hardware level verification, FIR filter gives better frequency response than DCT filter.

Nowadays, with the development of high quality graphical softwares, almost every presentation, in addition to text, contains some kind of images too. According to the presentation needs, different kinds of images are used by the presenters but different kinds of images needs different type of treatments which evolve the image categorization research. In our work we try to categorize images into two broad groups as Geometrical and Non-geometrical. An important characteristic of the proposed model is that specific matching techniques, suitable for a particular domain, can be developed and easily adopted to a system which will reduce the search domain and increase the accuracy in similarity matching. A classifier has been developed by using novel features. These features are devised based on color projection and used to differentiate geometrical images from ordinary images.

In recent time, ultrasound imaging is a popular modality for various medical applications. The presence of speckle noise affects difficulties on features extraction and quantitative measurement of ultrasound images. This paper proposes a new method to suppress the speckle noise while attempting to preserve the image content using combination of Gaussian filter and discrete cosine transform (DCT) approach. The proposed method, called quasi-Gaussian DCT (QGDCT) filter, is a quasi Gaussian filter in which its coefficients are derived from a selected 2-dimensional cosine basis function. The Gaussian approach is used to suppress speckle noise whereas the selected DCT approach is intended to preserve the image content. The filter will be implemented on the synthetic speckle images and the clinical echocardiograph ultrasound images. To evaluate the effectiveness of the filter, several quantitative measurements such as mean square error, peak signal to noise ration, speckle suppression index and speckle statistical analysis, are computed and analyzed. In comparison with established filters, results obtained confirmed the effectiveness of QGDCT filter in suppressing speckle noise and preserving the image content.

Image analyzing method to detect vague boundaries by using reaction–diffusion system

Delineation of line patterns in images is a basic step required in various applications such as blood vessel detection in medical images, segmentation of rivers or roads in aerial images, detection of cracks in walls or pavements, etc. In this paper we present trainable B-COSFIRE filters, which are a model of some neurons in area V1 of the primary visual cortex, and apply it to the delineation of line patterns in different kinds of images. B-COSFIRE filters are trainable as their selectivity is determined in an automatic configuration process given a prototype pattern of interest. They are configurable to detect any preferred line structure (e.g. segments, corners, cross-overs, etc.), so usable for automatic data representation learning. We carried out experiments on two data sets, namely a line-network data set from INRIA and a data set of retinal fundus images named IOSTAR. The results that we achieved confirm the robustness of the proposed approach and its effectiveness in the delineation of line structures in different kinds of images.

Human recognition systems have gained a considerable attention during last decade due to its vast applications in the field of computer and advantages over previous biometric methods. There are many applications with respect to security, sensitivity and secrecy. Face detection is the most important and first step of recognition system. Human detection suffers from various challenges due to variation regarding image conditions, size, resolution, poses and rotation. Its accurate and robust detection has been a great task for the researchers. There exist various numbers of methods and techniques for detection but none can guarantee successful in all conditions for all kinds of faces and images. Some methods are exhibiting good results in certain conditions and others are good with different kinds of images. Face detection based on skin color is found to be more effective technique because of the properties of skin color which is unique and can be easily separated from the other objects present in the image and background. This paper introduces a new approach to detection systems using the skin color of a subject. This system can detect a regardless of the background of the picture, which is an important phase for identification. The images used in this system are color images which give additional information about the images than the gray images provide. In detection, the two respective classes are the face and the non-face area. This new approach to detection is based on color tone values specially defined for skin area detection within the image frame.

In the automatic classification of colored natural textures, the idea of proposing methods that reflect human perception arouses the enthusiasm of researchers in the field of image processing and computer vision. Therefore, the color space and the methods of analysis of color and texture, must be discriminating to correspond to the human vision. Rock images are a typical example of natural images and their analysis is of major importance in the rock industry. In this paper, we combine the statistical (Local Binary Pattern (LBP) with Hue Saturation Value (HSV) and Red Green Blue (RGB) color spaces fusion) and frequency (Gabor filter and Discrete Cosine Transform (DCT)) descriptors named respectively Gabor Adjacent Local Binary Pattern Color Space Fusion (G-ALBPCSF) and DCT Adjacent Local Binary Pattern Color Space Fusion (D-ALBPCSF) for the extraction of visual textural and colorimetric features from direct view images of rocks. The textural images from the two G-ALBPCSF and D-ALBPCSF approaches are evaluated through similarity metrics such as Chi2 and the intersection of histograms that we have adapted to color histograms. The results obtained allowed us to highlight the discrimination of the rock classes. The proposed extraction method provides better classification results for various direct view rock texture images. Then it is validated by a confusion matrix giving a low error rate of 0.8% of classification.

This paper presents a comparatively simple approach for showthrough and strikethrough print defect detection using computer vision method. Showthrough and strikethrough are common printing problem and are typically functions of a paper’s opacity. Under normal lighting condition the visibility of printing on the reverse side of printed paper is termed as showthrough whereas the penetration of ink to the other side is termed as strikethrough. Moreover the intensity of showthrough pixel is extremely low thus it is difficult to identify the showthrough pixel from the printed area. On the other hand strikethrough is the result of penetration of ink through paper and depends on the absorbent nature of paper. Comparatively the intensity of the strikethrough pixel is higher than that of the showthrough but due to similar intensity of the ink of the printed pixel and strikethrough pixel, both overlapped with each other in the foreground of the image. These print defects can degrade the image quality as well as print production. In this study, the detection of these two print defects achieved using histogram equalization technique, to enhance the contrast between foreground and back ground pixels. A global thresholding algorithm was applied on a his-togram equalized image to segment the printed area from the background of the image. Pixels in the background which are considered as showthrough and strike through pixels are identified by image subtraction. The pictorial representations of the results show the remarkable potential of the proposed technique which can be possible alternative of present subjective measures of showthrough and strikethrough.