Efficient Color Correction Using Normalized Singular Value for Duststorm Image Enhancement

A duststorm image has a reddish or yellowish color cast. Though a duststorm image and a hazy image are obtained using the same process, a hazy image has no color distortion as it has not been disturbed by particles, but a duststorm image has color distortion owing to an imbalance in the color channel, which is disturbed by sand particles. As a result, a duststorm image has a degraded color channel, which is rare in certain channels. Therefore, a color balance step is needed to enhance a duststorm image naturally. This study goes through two steps to improve a duststorm image. The first is a color balance step using singular value decomposition (SVD). The singular value shows the image’s diversity features such as contrast. A duststorm image has a distorted color channel and it has a different singular value on each color channel. In a low-contrast image, the singular value is low and vice versa. Therefore, if using the channel’s singular value, the color channels can be balanced. Because the color balanced image has a similar feature to the haze image, a dehazing step is needed to improve the balanced image. In general, the dark channel prior (DCP) is frequently applied in the dehazing step. However, the existing DCP method has a halo effect similar to an over-enhanced image due to a dark channel and a patch image. According to this point, this study proposes to adjustable DCP (ADCP). In the experiment results, the proposed method was superior to state-of-the-art methods both subjectively and objectively.

CARNet: Cascade attentive RefineNet for multi-lesion segmentation of diabetic retinopathy images

Diabetic retinopathy is the leading cause of blindness in working population. Lesion segmentation from fundus images helps ophthalmologists accurately diagnose and grade of diabetic retinopathy. However, the task of lesion segmentation is full of challenges due to the complex structure, the various sizes and the interclass similarity with other fundus tissues. To address the issue, this paper proposes a cascade attentive RefineNet (CARNet) for automatic and accurate multi-lesion segmentation of diabetic retinopathy. It can make full use of the fine local details and coarse global information from the fundus image. CARNet is composed of global image encoder, local image encoder and attention refinement decoder. We take the whole image and the patch image as the dual input, and feed them to ResNet50 and ResNet101, respectively, for downsampling to extract lesion features. The high-level refinement decoder uses dual attention mechanism to integrate the same-level features in the two encoders with the output of the low-level attention refinement module for multiscale information fusion, which focus the model on the lesion area to generate accurate predictions. We evaluated the segmentation performance of the proposed CARNet on the IDRiD, E-ophtha and DDR data sets. Extensive comparison experiments and ablation studies on various data sets demonstrate the proposed framework outperforms the state-of-the-art approaches and has better accuracy and robustness. It not only overcomes the interference of similar tissues and noises to achieve accurate multi-lesion segmentation, but also preserves the contour details and shape features of small lesions without overloading GPU memory usage.

Empirical Evaluation on Utilizing CNN-Features for Seismic Patch Classification

This paper empirically evaluates two kinds of features, which are extracted, respectively, with traditional statistical methods and convolutional neural networks (CNNs), in order to improve the performance of seismic patch image classification. In the latter case, feature vectors, named “CNN-features”, were extracted from one trained CNN model, and were then used to learn existing classifiers, such as support vector machines. In this case, to learn the CNN model, a technique of transfer learning using synthetic seismic patch data in the source domain, and real-world patch data in the target domain, was applied. The experimental results show that CNN-features lead to some improvements in the classification performance. By analyzing the data complexity measures, the CNN-features are found to have the strongest discriminant capabilities. Furthermore, the transfer learning technique alleviates the problems of long processing times and the lack of learning data.

FrHPI: A Discriminative Patch-Image Model for Hyperspectral Anomaly Detection

Anomaly detection is now a significantly important part of hyperspectral image analysis to detect targets in an unsupervised manner. Traditional hyperspectral anomaly detectors fail to consider spatial information, which is vital in hyperspectral anomaly detection. Moreover, they usually take the raw data without feature extraction as input, limiting the detection performance. We propose a new anomaly detector based on the fractional Fourier transform (FrFT) and a modified patch-image model called the hyperspectral patch-image (HPI) model to tackle these two problems. By combining them, the proposed anomaly detector is named fractional hyperspectral patch-image (FrHPI) detector. Under the assumption that the target patch-image is a sparse matrix while the background patch-image is a low-rank matrix, we first formulate a matrix by sliding a rectangle window on the first three principal components (PCs) of HSI. The matrix can be decomposed into three parts representing the background, targets, and noise with the well-known low-rank and sparse matrix decomposition (LRaSMD). Then, distinctive features are extracted via FrFT, a transformation which is desirable for noise removal. Background atoms are selected to construct the covariance matrix. Finally, anomalies are picked up with Mahalanobis distance. Extensive experiments are conducted to verify the proposed FrHPI detector’s superiority in hyperspectral anomaly detection compared with other state-of-the-art detectors.