{"id":8182,"date":"2012-09-10T15:38:54","date_gmt":"2012-09-10T12:38:54","guid":{"rendered":"http:\/\/hgpu.org\/?p=8182"},"modified":"2012-09-10T15:38:54","modified_gmt":"2012-09-10T12:38:54","slug":"cuneuquant-a-cuda-implementation-of-the-neuquant-image-quantization-algorithm","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=8182","title":{"rendered":"CuNeuQuant: A CUDA Implementation of the NeuQuant Image Quantization Algorithm"},"content":{"rendered":"<p>Color quantization is an often performed prestep in many image processing and computer vision applications. Quantization is defined as the process of selecting a palette of representative colors P which can replace the original colors C in an image such that |P| &lt;&lt; |C| and the perceptual distortion of the reduced color image is minimized. It is well known that the quantization process is an NP-complete problem and as such, many competing heuristic algorithms exist. One high-quality quantization algorithm is NeuQuant due to Dekker. In this paper, we describe a GPU based parallel implementation of the NeuQuant algorithm. Our GPU-based approach demonstrated a speedup by a factor of 5 or more in the performance evaluation we have performed. The details of the NeuQuant algorithm present unique difficulties to implementing a parallel version due to the sequential dependencies present when training the underlying neural network.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Color quantization is an often performed prestep in many image processing and computer vision applications. Quantization is defined as the process of selecting a palette of representative colors P which can replace the original colors C in an image such that |P| &lt;&lt; |C| and the perceptual distortion of the reduced color image is minimized. [&hellip;]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":false,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[36,73,89,33,3],"tags":[1787,1791,14,1786,34,20,411,176],"class_list":["post-8182","post","type-post","status-publish","format-standard","hentry","category-algorithms","category-computer-vision","category-nvidia-cuda","category-image-processing","category-paper","tag-algorithms","tag-computer-vision","tag-cuda","tag-image-processing","tag-neural-networks","tag-nvidia","tag-nvidia-geforce-9800-gtx","tag-package"],"views":4884,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/8182","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=8182"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/8182\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=8182"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=8182"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=8182"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}