Search

Just like many other topics in computer vision, image classification has achieved significant progress recently by using deep learning neural networks, especially the Convolutional Neural Networks (CNNs). Most of the existing works focused on classifying very clear natural images, evidenced by the widely used image databases, such as Caltech-256, PASCAL VOCs, and ImageNet. However, in many real applications, the acquired images may contain certain degradations that lead to various kinds of blurring, noise, and distortions. One important and interesting problem is the effect of such degradations to the performance of CNN-based image classification and whether degradation removal helps CNN-based image classification. More specifically, we wonder whether image classification performance drops with each kind of degradation, whether this drop can be avoided by including degraded images into training, and whether existing computer vision algorithms that attempt to remove such degradations can help improve the image classification performance. In this article, we empirically study those problems for nine kinds of degraded images—hazy images, motion-blurred images, fish-eye images, underwater images, low resolution images, salt-and-peppered images, images with white Gaussian noise, Gaussian-blurred images, and out-of-focus images. We expect this article can draw more interests from the community to study the classification of degraded images. [ABSTRACT FROM AUTHOR]

• We propose a novel Hybrid CNN architecture to address the problem of sketch recognition. • S-Net extracts shape features, which is invariant for sketch rotation and transformation. • Hybrid CNN achieves state-of-the-art on sketch classification and sketch-based image retrieval tasks. • The classification accuracy is 84.42% and 82.74% on TU-Berlin and SketchX datasets, respectively. • The MAP of SBIR is 57.4% and 28.74% on SketchX and Flickr15K-Large datasets, respectively. With the popularity of touch-screen devices, it is becoming increasingly important to understand users' free-hand sketches in computer vision and human-computer interaction. Most of existing sketch recognition methods employ the similar strategies used in image recognition, relying on appearance information represented by hand-crafted features or deep features from convolutional neural networks. We believe that sketch recognition can benefit from learning both appearance and shape representation. In this paper, we propose a novel architecture, named Hybrid CNN, which is composed of A-Net and S-Net. They describe appearance information and shape information, respectively. Hybrid CNN is then comprehensively evaluated in the sketch classification and retrieval tasks on different datasets, including TU-Berlin, Sketchy and Flickr15k. Experimental results demonstrate that the Hybrid CNN achieves competitive accuracy compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Although image inpainting is a challenging task in computer vision, most existing image inpainting methods have achieved remarkable progress. However, occlusion and low resolution often appear on one image simultaneously in the real world, and only a few methods can address low-resolution image inpainting. To tackle this problem, we propose a novel method called the Dual Resolution Generative Adversarial Network (DRGAN), which formulates low-resolution (LR) image inpainting as a constrained image generation problem. The proposed DRGAN first trains a generative network to obtain high-quality images from noise vectors. Then a dual-resolution loss is designed to effectively integrate both high- and low-resolution information to optimize the input vectors initialized by random noise to generate high-quality images. Compared with the model that learns the mapping function from low- to high-quality images, the proposed model maps input noise vectors to images and can thus adapt more effectively to various types of degradation and large occlusions. Extensive experiments on synthetic LR data and real-world images demonstrate the effectiveness of the proposed DRGAN. [ABSTRACT FROM AUTHOR]

A patrol type of surveillance has been performed everywhere from police city patrol to railway inspection. Different from static cameras or sensors distributed in a space, such surveillance has its benefits of low cost, long distance, and efficiency in detecting infrequent changes. However, the challenges are how to archive daily recorded videos in the limited storage space and how to build a visual representation for quick and convenient access to the archived videos. We tackle the problems by acquiring and visualizing route panoramas of rail scenes. We analyze the relation between train motion and the video sampling and the constraints such as resolution, motion blur and stationary blur etc. to obtain a desirable panoramic image. The route panorama generated is a continuous image with complete and non-redundant scene coverage and compact data size, which can be easily streamed over the network for fast access, maneuver, and automatic retrieval in railway environment monitoring. Then, we visualize the railway scene based on the route panorama rendering for interactive navigation, inspection, and scene indexing. [ABSTRACT FROM AUTHOR]