The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Conventional unsupervised image segmentation methods use color and geometric information and apply clustering algorithms over pixels. They preserve object boundaries well but often suffer from over-segmentation due to noise and artifacts in the images. In this paper, we contribute on a preprocessing step for image smoothing, which alleviates the burden of conventional unsupervised image segmentation...
Text detection is a difficult task due to the significant diversity of the texts appearing in natural scene images. In this paper, we propose a novel text descriptor, SPP-net, extracted by equipping the Convolutional Neural Network (CNN) with spatial pyramid pooling. We first compute the feature maps from the original text lines without any cropping or warping, and then generate the fixed-size representations...
Conventional unsupervised image segmentation methods return many superpixels or object parts and thus tend to over-segmentation. In this paper, we present a novel post-processing approach for unsupervised object-level image segmentation (UnOLIS). Starting with the results of any conventional unsupervised segmentation method, we first combine a global region-based saliency and a robust background feature...
Image enhancement is a key technology in digital image processing. In this paper, a novel algorithm based on Laplacian pyramid transformation is proposed for enhancing hue invariability of color images. On the premise of hue invariability, the N-level Laplacian pyramid transform on saturation component of HIS space is performed to improve the saturation. Contrast limited adaptive histogram equalization...
Image saliency attempts to describe the most conspicuous part in an input image by mimicking human visual selective attention mechanism. Naturally, it could be adopted for improving object recognition. To demonstrate the effectiveness of saliency in object recognition, this paper proposes a salient hierarchical model. First, the traditional saliency model is modified for more robust saliency estimation...
In this paper, we present a novel pixel-level color-image fusion method with extension of the joint sparsity model which exploits the inter-correlations among the R, G and B planes. The objective is to achieve the colors more natural for the fused images, compared to individually reconstructing the R, G, B images. This paper also demonstrates an extension of the fusion algorithm to the proper handling...
Large-scale virtual terrain has broadly been used in many fields, such as battlefield simulation, video game, films, GIS etc. Based on analyzing existing algorithms of creating virtual terrains, this paper presents a novel algorithm to synthesize large-scale virtual terrain from an image set. Firstly, many realistic terrain-blocks are generated by processing images properly. Then, based on definition...
In this paper, a novel texture feature GMACM, is presented according to the statistics of gradient angle cooccurrence in color images. Based on three different types of gradients defined in the RGB space, the corresponding GMACMs are introduced. With some well-designed color image classification experiments, it is shown that GMACMs outperform GLCM and Gabor filters significantly in efficiency and...
Image classification is an important problem in computer vision. All existing image classification approaches tend to classify images of distinctly different objects. In this paper, we attempt to classify two similar image classes, Chinese and European classical architecture. First, Gabor filter is utilized to catch texture features of images. Then color histogram distance is adopted as a coefficient...
A novel region-based color mapping method is proposed to render fused image of visible and infrared (IR). The method is based on image segmentation, region recognition, image fusion and color transfer. Firstly visible image and IR image are fused based on the curvelet transform. At the same time, a color database is formed by grouping a set of natural color images according to their scene contents...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.