By Kai Zeng, Zhou Wang (auth.), Mohamed Kamel, Aurélio Campilho (eds.)

The two-volume set LNCS 6753/6754 constitutes the refereed court cases of the eighth foreign convention on snapshot and popularity, ICIAR 2011, held in Burnaby, Canada, in June 2011. The eighty four revised complete papers offered have been conscientiously reviewed and chosen from 147 submissions. The papers are equipped in topical sections on picture and video processing; function extraction and trend acceptance; laptop imaginative and prescient; colour, texture, movement and form; monitoring; biomedical photograph research; biometrics; face reputation; snapshot coding, compression and encryption; and applications.

Show description

Read Online or Download Image Analysis and Recognition: 8th International Conference, ICIAR 2011, Burnaby, BC, Canada, June 22-24, 2011. Proceedings, Part I PDF

Best analysis books

Analysis of Reliability and Quality Control: Fracture Mechanics 1

This primary publication of a 3-volume set on Fracture Mechanics is especially established at the giant diversity of the legislation of statistical distributions encountered in numerous medical and technical fields. those legislation are vital in realizing the chance habit of parts and mechanical constructions which are exploited within the different volumes of this sequence, that are devoted to reliability and quality controls.

Extra resources for Image Analysis and Recognition: 8th International Conference, ICIAR 2011, Burnaby, BC, Canada, June 22-24, 2011. Proceedings, Part I

Example text

Secondly, despite the Nelder-Mead simplex algorithm is reportedly faster than other direct search algorithms, the proposed method is still slower than state-of-the-art techniques. 4GHz for 320 × 240 pixels grey-level images. Dynamic down-sampling of images during optimization is a possible way of reducing the computational cost, and will be evaluated in a future work. 6 Conclusion This paper presents an original method that replaces the projection/reconstruction step of the standard Eigenbackground algorithm with a direct background image generation.

In this paper we present a new example-based method that uses the input low-resolution image itself as a search space for high-resolution patches by exploiting self-similarity across different resolution scales. Found examples are combined in a highresolution image by the means of Markov Random Field modelling that forces their global agreement. Additionally, we apply back-projection and steering kernel regression as post-processing techniques. In this way, we are able to produce sharp and artefact-free results that are comparable or better than standard interpolation and state-of-the-art super-resolution techniques.

18 T. Ruˇzi´c et al. Fig. 6. Cropped version of man image 2x magnification. From left to right: bi-cubic result, result of [14], result of the proposed method. output of the MRF, without any post-processing, gives already reasonably good results. For example, all edges are sharp without “jaggy” artefacts which are visible in the result of bi-cubic interpolation. g. texture on the roof). Finally, kernel regression only slightly smooths the image and can even be left out as a post-processing step in this case.

Download PDF sample

Rated 4.15 of 5 – based on 28 votes