Spatio-spectral networks for color-texture analysis

The present work proposes the development of a novel method to provide descriptors for colored texture images. The method consists of two steps. First, we apply a linear transform in the color space of the image aiming at highlighting spatial structuring relations among the color of pixels. Second, we apply a multiscale approach to the calculus of fractal dimension based on Fourier transform. From this multiscale operation, we extract the descriptors that are used to discriminate the texture represented in digital images. The accuracy of the method is verified in the classification of two color texture datasets, by comparing the performance of the proposed technique to other classical and state-of-the-art methods for color texture analysis. The results showed an advantage of almost 3% of the proposed technique over the second best approach.

Local Binary Patterns (LBPs) have been highly used in texture classification for their robustness, their ease of implementation and their low computational cost. Initially designed to deal with gray level images, several methods based on them in the literature have been proposed for images having more than one spectral band. To achieve it, whether assumption using color information or combining spectral band two by two was done. Those methods use micro structures as texture features. In this paper, our goal was to design texture features which are relevant to color and multicomponent texture analysis without any assumption. Based on methods designed for gray scale images, we find the combination of micro and macro structures efficient for multispectral texture analysis. The experimentations were carried out on color images from Outex databases and multicomponent images from red blood cells captured using a multispectral microscope equipped with 13 LEDs ranging from 375 nm to 940 nm. In all achieved experimentations, our proposal presents the best classification scores compared to common multicomponent LBP methods. 99.81%, 100.00%, 99.07% and 97.67% are maximum scores obtained with our strategy respectively applied to images subject to rotation, blur, illumination variation and the multicomponent ones.

In this paper, we systematically review recent advances in surface inspection using computer vision andimage processing techniques, particularly those based on texture analysis methods. The aim is to reviewthe state-of-the-art techniques for the purposes of visual inspection and decision making schemes that areable to discriminate the features extracted from normal and defective regions. This field is so vast that itis impossible to cover all the aspects of visual inspection. This paper focuses on a particular but importantsubset which generally treats visual surface inspection as texture analysis problems. Other topics related tovisual inspection such as imaging system and data acquisition are out of the scope of this survey.The surface defects are loosely separated into two types. One is local textural irregularities which is themain concern for most visual surface inspection applications. The other is global deviation of colour and/ortexture, where local pattern or texture does not exhibit abnormalities. We refer this type of defects as shadeor tonality problem. The second type of defects have been largely neglected until recently, particularly whencolour imaging system has been widely used in visual inspection and where chromatic consistency plays animportant role in quality control. The emphasis of this survey though is still on detecting local abnormalities,given the fact that majority of the reported works are dealing with the first type of defects.The techniques used to inspect textural abnormalities are discussed in four categories, statistical approaches,structural approaches, filter based methods, and model based approaches, with a comprehensivelist of references to some recent works. Due to rising demand and practice of colour texture analysis inapplication to visual inspection, those works that are dealing with colour texture analysis are discussedseparately. It is also worth noting that processing vector-valued data has its unique challenges, which conventionalsurface inspection methods have often ignored or do not encounter.We also compare classification approaches with novelty detection approaches at the decision makingstage. Classification approaches often require supervised training and usually provide better performancethan novelty detection based approaches where training is only carried out on defect-free samples. However,novelty detection is relatively easier to adapt and is particularly desirable when training samples areincomplete

Predictive analysis on cellular traffic is important for the control and monitoring of wireless networks. Cellular traffic prediction is a challenging problem due to the non- stationarity and dynamic spatial-temporal correlation of the traffic. In this paper, we address the problem of accurate traffic prediction in a base station by proposing a deep neural network called RAConv. Its structure includes residual network, attention mechanism, and deep convolutional network. In the proposed architecture, a deep 3D residual convolutional network (ResConv3D) with three residual blocks are employed to learn the local spatial-temporal features. An attention-aided convolutional long short-term memory network (AConvLSTM) is then used to capture the long-term spatial-temporal dependencies. The use of the attention modules enable the network to focus on the most important spatial-temporal information. We evaluate the performance of the proposed RAConv network using a dataset provided by a Canadian wireless service provider. We consider the traffic prediction on two time scales (i.e., hourly and daily), which exhibit different spatial-temporal dependency patterns. Experimental results show that the proposed RAConv network can achieve accurate prediction under both time scales. Results also show that our proposed network provides a lower root-mean-square error (RMSE) than the conventional ConvLSTM baseline scheme.

Color models are widely used in image recognition because they represent significant information. On the other hand, texture analysis techniques have been extensively used for facial feature extraction. In this paper; we extract discriminative features related to facial attributes by utilizing different color models and texture analysis techniques. Specifically, we propose novel methods for texture analysis to improve classification performance of race and gender. The proposed methods for texture analysis are based on Local Binary Pattern and its derivatives. These texture analysis methods are evaluated for six color models (hue, saturation and intensity value (HSV); L*a*b*; RGB; YCbCr; YIQ; YUV) to investigate the effect of each color model. Further, we configure two combinations of color channels to represent color information suitable for gender and race classification of face images. We perform experiments on publicly available face databases. Experimental results show that the proposed approaches are effective for the classification of gender and race.

In this article, we present an adaptive color similarity function defined in a modified hue‐saturation‐intensity color space, which can be used directly as a metric to obtain pixel‐wise segmentation of color images among other applications. The color information of every pixel is integrated as a unit by an adaptive similarity function thus avoiding color information scattering. As a direct application we present an efficient interactive, supervised color segmentation method with linear complexity respect to the number of pixels of the input image. The process has three steps: (1) Manual selection of few pixels in a sample of the color to be segmented. (2) Automatic generation of the so called color similarity image (CSI), which is a gray level image with all the gray level tonalities associated with the selected color. (3) Automatic threshold of the CSI to obtain the final segmentation. The proposed technique is direct, simple and computationally inexpensive. The evaluation of the efficiency of the color segmentation method is presented showing good performance in all cases of study. A comparative study is made between the behavior of the proposed method and two comparable segmentation techniques in color images using (1) the Euclidean metric of thea* andb* color channels rejectingL* and (2) a probabilistic approach ona* andb* in the CIE L*a*b* color space. Our testing system can be used either to explore the behavior of a similarity function (or metric) in different color spaces or to explore different metrics (or similarity functions) in the same color space. It was obtained from the results that the color parametersa* andb* are not independent of the luminance parameterL* as one might initially assume in the CIE L*a*b* color space. We show that our solution improves the quality of the proposed color segmentation technique and its quick result is significant with respect to other solutions found in the literature. The method also gives a good performance in low chromaticity, gray level and low contrast images. © 2016 Wiley Periodicals, Inc. Col Res Appl, 42, 156–172, 2017

Malaria is a disease in human caused by Plasmodium parasite. Misdiagnosis and improperness in medical treatment towards this disease can lead to the death of patients. A number of digital image analysis-based research works to minimize the misdiagnosis has been developed. This research aims to segment the form of parasitic cells of Plasmodium using the combination of the red (R) channel in the RGB color space and saturation (S) channel in the HSV color space. The images used were parasitic cells of Plasmodium vivax, consisting of the phases of trophozoite, schizonts, and gametocytes. Each of which comprises ten samples. The process was begun by improving the image quality continued by separating the red channel in the RGB color space and by converting the image of RGB into the HSV image to obtain the saturation (S) channel. These two color channels were then combined in the form of a grayscale image. The further process was conducted by changing those grayscale image into the binary image using the Otsu method and the morphological operation to form it as the masking image. Of 30 tested images, the segmentation of the red (R) channel and saturation (S) channel combination achieved the accuracy of 93.33%, while the segmentation using saturation (S) channel produces result in the accuracy of 66.67%.

Patients with cerebral haemorrhages need to drain haematomas. Fresh blood may appear during the haematoma drainage process, so this needs to be observed and detected in real time. To solve this problem, this paper studies images produced during the haematoma drainage process. A blood image feature selection recognition and classification framework is designed. First, aiming at the characteristics of the small colour differences in blood images, the general RGB colour space feature is not obvious. This study proposes an optimal colour channel selection method. By extracting the colour information from the images, it is recombined into a 3 × 3 matrix. The normalised 4‐neighbourhood contrast and variance are calculated for quantitative comparison. The optimised colour channel is selected to overcome the problem of weak features caused by a single colour space. After that, the effective region in the image is intercepted, and the best colour channel of the image in the region is transformed. The first, second and third moments of the three best colour channels are extracted to form a nine‐dimensional eigenvector. K‐means clustering is used to obtain the image eigenvector, outliers are removed, and the results are then transferred to the hidden Markov model (HMM) and support vector machine (SVM) for classification. After selecting the best color channel, the classification accuracy of HMM‐SVM is greatly improved. Compared with other classification algorithms, the proposed method offers great advantages. Experiments show that the recognition accuracy of this method reaches 98.9%.

This paper proposes a method of accurately assessing image quality without a reference image by using a deep convolutional neural network. Existing training based methods usually utilize a compact set of linear filters for learning features of images captured by different sensors to assess their quality. These methods may not be able to learn the semantic features that are intimately related with the features used in human subject assessment. Observing this drawback, this work proposes training a deep convolutional neural network (CNN) with labelled images for image quality assessment. The ReLU in the CNN allows non-linear transformations for extracting high-level image features, providing a more reliable assessment of image quality than linear filters. To enable the neural network to take images of any arbitrary size as input, the spatial pyramid pooling (SPP) is introduced connecting the top convolutional layer and the fully-connected layer. In addition, the SPP makes the CNN robust to object deformations to a certain extent. The proposed method taking an image as input carries out an end-to-end learning process, and outputs the quality of the image. It is tested on public datasets. Experimental results show that it outperforms existing methods by a large margin and can accurately assess the image quality on images taken by different sensors of varying sizes.

Large convolutional networks have achieved impressive classification performances recently. To achieve better performance, convolutional network tends to develop into deeper. However, the increase of network depth causes the linear growth of computational complexity, but cannot bring equivalent increase to the classification accuracy. To alleviate this inconsistence, we propose a cascading approach to accelerate the classification of very deep convolutional neural network. By exploiting the entropy metric to analyze the statistic differences of basic networks between the correctly and mistakenly classified images, we can assign the easily distinguished images to the shallow networks for reducing the computational complexity, and leave the difficultly classified images to the deep networks for maintaining the overall performance. Besides, the proposed cascaded networks can take advantage of the complementarity between different networks, which may boost the classification accuracy compared to the deepest network. We perform the experiments using residual networks of different depths on cifar100 dataset, on the condition of obtaining the similar accuracy to the deepest network, the results show that our cascaded ResNet32-ResNet110 and cascaded ResNet32-ResNet164 can reduce the computation time by 48.6% and 44.3% compared to ResNet110 and ResNet164, respectively. And the cascaded ResNet32-ResNet110-ResNet164 can reduce the computation time by 85.4% compared to the very deep Resnet1001.

This paper concerns the problem of frog and haze image enhancement. Images are often degreed due to the fog and haze condition. In this paper, an image enhancement method by using improved histogram equalization in HIS color space was put forward. Firstly, the image was transformed from RGB to HIS color space. Then the S and I components were treated with improved histogram equalization separately. When judging whether a gray level was to be merged with another, the weight coefficients with increased step were assigned to these low frequency gray levels according to their distance to the current gray level. Thus the excessive gray level merging was avoided. At the same time, a non-linear gray level mapping algorithm was proposed, which improved the contrast and brightness of the image. The experimental results show that our methods could keep the original colors and details of the image better, and they could improve the frog and haze image display effects significantly.

Electrochemical machining is a promising non-traditional manufacturing process to make high-quality parts. The benefits of minimal thermally and mechanically induced stresses, free of burr, and a low surface roughness are appealing for industry and research institutes. However, the combined chemical reaction, electric field, fluid mechanics, and material properties involve a significant number of independent parameters which are difficult to analyze in order to draw comprehensive conclusions. To our current knowledge, process responses such as the material removal rate, optimal feed rate, and cutting profile cannot be represented accurately by analytical solutions. In recent years, deep learning has had tremendous success in analyzing sophisticated systems. The improved computation efficiency and reduced size of the training dataset required for deep learning have enabled various prediction models in the manufacturing industry. In this paper, a new approach is developed using the deep convolutional network with the Bayesian optimization algorithm to predict the diameters of the drilled hole from an electrochemical machining process. The Keras application programming interface (API) was used to build the deep convolutional network; the feed rate, pulse-on time, and voltage were used as input parameters to provide a fair comparison with a neural network from previous research. Random dropout layers were added to prevent overfitting of the network. Instead of tuning the network parameter by trial and error, the Bayesian parameter optimization algorithm was implemented to find the optimal set of parameters of the deep convolutional network that yields the minimum mean square error. The proposed algorithm was compared with a previously developed neural network with partially embedded physical knowledge. Improved training speed and accuracy were observed in comparison with the traditional neural network. The prediction model using the proposed deep learning algorithm demonstrated better prediction accuracy and provided a more systematic way to select the hyperparameter for the deep convolutional network.

This paper describes a color space optimized for processing images of uniformly colored objects. Standard RGB color space is an ineffective space for this type of processing due to the high cross-correlation between color channels. The proposed /spl beta//spl delta//spl epsiv/ color space establishes a primary axis containing the expected color range of the object. The second and third coordinates contain magnitude and chromaticity of any deviation from the expected color. The separation into application specific coordinates is the main advantage of the new color space. The new color space has been used in two industrial inspection systems and has been implemented in hardware.

Computer-aided diagnosis of ocular disorders like glaucoma can be effectively performed with retinal fundus images. Since the advent of machine learning and later deep learning techniques in medical image analysis, research focusing on automated and early detection of glaucoma has gained prominence. In this paper, we show how a deep Convolutional Neural Network model can be used in visualising the features related to Glaucoma that are consistent with (a subset of) those used by ophthalmologists for diagnosis. However, since the doctors do not necessarily depend entirely on these features but back them up with other important measurements such as visual field testing (HVF), any deep neural network such as CNN may not necessarily be expected to yield 100% accuracy. Further, other important parameters such as Intraocular Pressure (IOP), which may be built into a deep learning model, may not necessarily correlate well with the presence of Glaucoma. In this work, a deep CNN model has been trained and tested on a large number of high-quality fundus images, both normal and glaucomatous. We compare the results with transfer learning models such as VGG16, ResNet50, and MobileNetV2. On an average, we obtained an accuracy of 93.75% in identifying glaucoma, focusing only on the features of the fundus image.

A novel local mesh color texture pattern for image retrieval system