Perceptual color image coding with JPEG2000

Texture characterization and classification of polarized images based on multi-angle orthogonal difference

The Local Binary Pattern (LBP) and its variants are capable of extracting image texture and have been successfully applied to classification. However, LBP has not been used to extract and describe the texture of polarized images, and simple LBP cannot characterize the polarized texture information from different polarizations of angles. In order to solve these problems, we propose a new multi-angle orthogonal difference polarization image texture descriptor (MODP_ITD) by analyzing the relationship between the difference of orthogonal difference polarization images from different angles and the pixel intensity distribution in the local neighborhood of images from different angles. The MODP_ITD consists of three patterns: multi-angle polarization orthogonal difference local binary pattern (MODP_LBP), multi-angle polarization orthogonal difference local sampling point principal component sequence pattern (MODP_LPCSP) and multi-angle orthogonal difference polarization local difference binary pattern (MODP_LDBP). The MODP_LBP extracts local corresponding texture characteristics of polarized orthogonal difference images from multiple angles. The MODP_LPCSP sorts the principal component order of each angle orthogonal difference local sampling point. The MODP LDBP extracts the local difference characteristics between different angles by constructing a new polarized image. Then, the frequency histograms of MODP_LBP, MOD_LPCSP ,and MODP_LDBP are cascaded to generate MODP_ITD, so as to distinguish local neighborhoods. By using vertical and parallel polarization and unpolarized light active illumination, combined with the measurements at three different detection zenith angles, we constructed a polarization texture image database. A substantial number of experimental results on the self-built database show that our proposed MODP_ITD can represent the detailed information of polarization images texture. In addition, compared with the existing LBP methods, The MODP_ITD has a competitive advantage in classification accuracy.

Visibility of Quantization Errors in Reversible JPEG2000

Image compression systems that exploit the properties of the human visual system have been studied extensively over the past few decades. For the JPEG2000 image compression standard, all previous methods that aim to optimize perceptual quality have considered the irreversible pipeline of the standard. In this work, we propose an approach for the reversible pipeline of the JPEG2000 standard. We introduce a new methodology to measure visibility of quantization errors when reversible color and wavelet transforms are employed. Incorporation of the visibility thresholds using this methodology into a JPEG2000 encoder enables creation of scalable codestreams that can provide both near-threshold and numerically lossless representations, which is desirable in applications where restoration of original image samples is required. Most importantly, this is the first work that quantifies the bitrate penalty incurred by the reversible transforms in near-threshold image compression compared to the irreversible transforms.

Understanding unconventional preprocessors in deep convolutional neural networks for face identification

Deep convolutional neural networks have achieved huge successes in application domains like object and face recognition. The performance gain is attributed to different facets of the network architecture such as: depth of the convolutional layers, activation function, pooling, batch normalization, forward and back propagation and many more. However, very little emphasis is made on the preprocessor’s module of the network. Therefore, in this paper, the network’s preprocessing module is varied across different preprocessing approaches while keeping constant other facets of the deep network architecture, to investigate the contribution preprocessing makes to the network. Commonly used preprocessors are the data augmentation and normalization and are termed conventional preprocessors. Others are termed the unconventional preprocessors, they are: color space converters; grey-level resolution preprocessors; full-based and plane-based image quantization, Gaussian blur, illumination normalization and insensitive feature preprocessors. To achieve fixed network parameters, CNNs with transfer learning is employed. The aim is to transfer knowledge from the high-level feature vectors of the Inception-V3 network to offline preprocessed LFW target data; and features is trained using the SoftMax classifier for face identification. The experiments show that the discriminative capability of the deep networks can be improved by preprocessing RGB data with some of the unconventional preprocessors before feeding it to the CNNs. However, for best performance, the right setup of preprocessed data with augmentation and/or normalization is required. Summarily, preprocessing data before it is fed to the deep network is found to increase the homogeneity of neighborhood pixels even at reduced bit depth which serves for better storage efficiency.

Structure descriptor based on just noticeable difference for texture image classification

Local binary pattern (LBP) and its derivates have been widely used in texture classification. However, LBP-based methods are sensitive to noise, and some structure information represented by non-uniform patterns is lost due to the combination of these patterns. In this paper, a new local structure descriptor based on just noticeable difference (JND) for texture classification is proposed by exploring the spatial and relative intensity correlations among local neighborhood pixels. First, a JND map of the image is computed, and then we attempt to model the correlations among local neighborhood pixels by comparing the absolute differences in intensity between the central pixel and its neighbors with the corresponding JND threshold. A new visual pattern (JNDVP) is designed using modeled correlations to describe image structure. Next, considering that image contrast makes important contributions to structure description, contrast is employed as a weighting factor for JNDVP histogram creation to represent structural and contrast information in a single representation. Finally, the nearest neighborhood classifier is employed for texture classification. Results on two texture image databases demonstrate that the proposed structure descriptor is rotation invariant and more robust to noise than LBP. Moreover, texture classification based on JNDVP outperforms LBP-based methods.

Development of an algorithm to automatically compress a CT image to visually lossless threshold

BACKGROUND

To develop an algorithm to predict the visually lossless thresholds (VLTs) of CT images solely using the original images by exploiting the image features and DICOM header information for JPEG2000 compression and to evaluate the algorithm in comparison with pre-existing image fidelity metrics.

METHODS

Five radiologists independently determined the VLT for 206 body CT images for JPEG2000 compression using QUEST procedure. The images were divided into training (n = 103) and testing (n = 103) sets. Using the training set, a multiple linear regression (MLR) model was constructed regarding the image features and DICOM header information as independent variables and regarding the VLTs determined with median value of the radiologists' responses (VLTrad) as dependent variable, after determining an optimal subset of independent variables by backward stepwise selection in a cross-validation scheme. The performance was evaluated on the testing set by measuring absolute differences and intra-class correlation (ICC) coefficient between the VLTrad and the VLTs predicted by the model (VLTmodel). The performance of the model was also compared two metrics, peak signal-to-noise ratio (PSNR) and high-dynamic range visual difference predictor (HDRVDP). The time for computing VLTs between MLR model, PSNR, and HDRVDP were compared using the repeated ANOVA with a post-hoc analysis. P < 0.05 was considered to indicate a statistically significant difference.

RESULTS

The means of absolute differences with the VLTrad were 0.58 (95% CI, 0.48, 0.67), 0.73 (0.61, 0.85), and 0.68 (0.58, 0.79), for the MLR model, PSNR, and HDRVDP, respectively, showing significant difference between them (p < 0.01). The ICC coefficients of MLR model, PSNR, and HDRVDP were 0.88 (95% CI, 0.81, 0.95), 0.85 (0.79, 0.91), and 0.84 (0.77, 0.91). The computing times for calculating VLT per image were 1.5 ± 0.1 s, 3.9 ± 0.3 s, and 68.2 ± 1.4 s, for MLR metric, PSNR, and HDRVDP, respectively.

CONCLUSIONS

The proposed MLR model directly predicting the VLT of a given CT image showed competitive performance to those of image fidelity metrics with less computational expenses. The model would be promising to be used for adaptive compression of CT images.

Exploratory study examining the at-home feasibility of a wearable tool for social-affective learning in children with autism

Although standard behavioral interventions for autism spectrum disorder (ASD) are effective therapies for social deficits, they face criticism for being time-intensive and overdependent on specialists. Earlier starting age of therapy is a strong predictor of later success, but waitlists for therapies can be 18 months long. To address these complications, we developed Superpower Glass, a machine-learning-assisted software system that runs on Google Glass and an Android smartphone, designed for use during social interactions. This pilot exploratory study examines our prototype tool’s potential for social-affective learning for children with autism. We sent our tool home with 14 families and assessed changes from intake to conclusion through the Social Responsiveness Scale (SRS-2), a facial affect recognition task (EGG), and qualitative parent reports. A repeated-measures one-way ANOVA demonstrated a decrease in SRS-2 total scores by an average 7.14 points (F(1,13) = 33.20, p = <.001, higher scores indicate higher ASD severity). EGG scores also increased by an average 9.55 correct responses (F(1,10) = 11.89, p = <.01). Parents reported increased eye contact and greater social acuity. This feasibility study supports using mobile technologies for potential therapeutic purposes.

Enhanced facial texture illumination normalization for face recognition

An uncontrolled lighting condition is one of the most critical challenges for practical face recognition applications. An enhanced facial texture illumination normalization method is put forward to resolve this challenge. An adaptive relighting algorithm is developed to improve the brightness uniformity of face images. Facial texture is extracted by using an illumination estimation difference algorithm. An anisotropic histogram-stretching algorithm is proposed to minimize the intraclass distance of facial skin and maximize the dynamic range of facial texture distribution. Compared with the existing methods, the proposed method can more effectively eliminate the redundant information of facial skin and illumination. Extensive experiments show that the proposed method has superior performance in normalizing illumination variation and enhancing facial texture features for illumination-insensitive face recognition.

New Sparse Facial Feature Description Model Based on Salience Evaluation of Regions and Features

Some regions (or blocks) and their affiliated features of face images are normally of more importance for face recognition. However, the variety of feature contributions, which exerts different saliency on recognition, is usually ignored. This paper proposes a new sparse facial feature description model based on salience evaluation of regions and features, which not only considers the contributions of different face regions, but also distinguishes that of different features in the same region. Specifically, the structured sparse learning scheme is employed as the salience evaluation method to encourage sparsity at both the group and individual levels for balancing regions and features. Therefore, the new facial feature description model is obtained by combining the salience evaluation method with region-based features. Experimental results show that the proposed model achieves better performance with much lower feature dimensionality.

Thermal-to-visible face recognition using partial least squares

Although visible face recognition has been an active area of research for several decades, cross-modal face recognition has only been explored by the biometrics community relatively recently. Thermal-to-visible face recognition is one of the most difficult cross-modal face recognition challenges, because of the difference in phenomenology between the thermal and visible imaging modalities. We address the cross-modal recognition problem using a partial least squares (PLS) regression-based approach consisting of preprocessing, feature extraction, and PLS model building. The preprocessing and feature extraction stages are designed to reduce the modality gap between the thermal and visible facial signatures, and facilitate the subsequent one-vs-all PLS-based model building. We incorporate multi-modal information into the PLS model building stage to enhance cross-modal recognition. The performance of the proposed recognition algorithm is evaluated on three challenging datasets containing visible and thermal imagery acquired under different experimental scenarios: time-lapse, physical tasks, mental tasks, and subject-to-camera range. These scenarios represent difficult challenges relevant to real-world applications. We demonstrate that the proposed method performs robustly for the examined scenarios.

An Evolutive Approach for Smile Recognition in Video Sequences

Facial expression recognition is one of the most challenging research areas in the image recognition field and has been actively studied since the 70's. For instance, smile recognition has been studied due to the fact that it is considered an important facial expression in human communication, it is therefore likely useful for human–machine interaction. Moreover, if a smile can be detected and also its intensity estimated, it will raise the possibility of new applications in the future. We are talking about quantifying the emotion at low computation cost and high accuracy. For this aim, we have used a new support vector machine (SVM)-based approach that integrates a weighted combination of local binary patterns (LBPs)-and principal component analysis (PCA)-based approaches. Furthermore, we construct this smile detector considering the evolution of the emotion along its natural life cycle. As a consequence, we achieved both low computation cost and high performance with video sequences.

COMPUTING IMAGE TEXTURE BY ISOPATTERN

Texture is an important feature that aids in identifying objects of interest or region of interest irrespective of the source of the image. In this paper, a novel and simple isopattern-based texture feature is introduced. Spatial gray scale dependencies represented by bit plane is analyzed for specific patterns and are accumulated in bins. These are scaled by half-normal weighting function to provide isopattern texture feature. The ability of this texture feature in capturing textural variations of the images despite the presence of illumination, scale and rotation is demonstrated by conducting texture analysis on Brodatz, OuTex texture datasets and its classification accuracy on Kylberg dataset. The results of these two experimentation indicate that the proposed textural feature picks variation in texture significantly and has a better texture classification accuracy of 98.26% when compared with the state-of-the-art features like Gabor, GLCM and LBP.

ILLUMINATION, SCALE AND ROTATION INVARIANT ALGORITHM FOR VISION-BASED UAV NAVIGATION

Navigation has been a major challenge for the successful operation of an autonomous aircraft. Although success has been achieved using active methods such as radar, sonar, lidar and the global positioning system (GPS), such methods are not always suitable due to their susceptibility to jamming and outages. Vision, as a passive navigation method, is considered as an excellent alternative; however, the development of vision-based autonomous systems for outdoor environments has proven difficult. For flying systems, this is compounded by the additional challenges posed by environmental and atmospheric conditions. In this paper, we present a novel passive vision-based algorithm which is invariant to illumination, scale and rotation. We use a three stage landmark recognition algorithm and an algorithm for waypoint matching. Our algorithms have been tested in both synthetic and real-world outdoor environments demonstrating overall good performance. We further compare our feature matching method with the speed-up robust features (SURF) method with results demonstrating that our method outperforms the SURF method in feature matching as well as computational cost.

Use of image features in predicting visually lossless thresholds of JPEG2000 compressed body CT images: initial trial

PURPOSE

To test the image features that may be useful in predicting the visually lossless thresholds (VLTs) of body computed tomographic (CT) images for Joint Photographic Experts Group 2000 (JPEG2000) compression.

MATERIALS AND METHODS

The institutional review board approved this study, with a waiver of informed patient consent. One hundred body CT studies obtained in different patients by using five scanning protocols were obtained, and 100 images, each of which was selected from each of the 100 studies, were collected. Five radiologists independently determined the VLT of each image for JPEG2000 compression by using the QUEST algorithm. The 100 images were randomly divided into two data sets-the training set (50 images) and the testing set (50 images)-and the division was repeated 200 times. For each of the 200 divisions, a multiple linear regression model was constructed on a training set and tested on a testing set regarding each of five image features-standard deviation of image intensity, image entropy, relative percentage of low-frequency (LF) energy, variation in high-frequency (HF) energy, and visual complexity-as independent variables and considering the VLTs determined with the median value of the radiologists' responses as a dependent variable. The root mean square residual and intraclass correlation coefficient (ICC) for the 200 divisions between the VLTs predicted by the models and those determined by radiologists were compared between the models by using repeated-measures analysis of variance with post-hoc comparisons.

RESULTS

Mean root-mean-square residuals for multiple linear regression models constructed with variation in HF energy (1.20 ± 0.10 [standard deviation]) and visual complexity (1.09 ± 0.07) were significantly lower than those for standard deviation of image intensity (1.65 ± 0.13), image entropy (1.63 ± 0.14), and relative percentage of LF energy (1.58 ± 0.12) (P < .01). ICCs for variation in HF energy (0.64 ± 0.05) and visual complexity (0.71 ± 0.04) were significantly higher than those for standard deviation of image intensity (0.04 ± 0.02), image entropy (0.05 ± 0.02), and relative percentage of LF energy (0.20 ± 0.04) (P < .01).

CONCLUSION

Among the five tested image features, variation in HF energy and visual complexity were the most promising in predicting the VLTs of body CT images for JPEG2000 compression.