Colour Appearance Descriptors for Image Browsing and Retrieval
نویسندگان
چکیده
In this paper, we focus on the development of whole-scene colour appearance descriptors for classification to be used in browsing applications. The descriptors can classify a whole-scene image into various categories of semantically-based colour appearance. Colour appearance is an important feature and has been extensively used in image-analysis, retrieval and classification. By using pre-existing global CIELAB colour histograms, firstly, we try to develop metrics for wholescene colour appearance: “colour strength”, “high/low lightness” and “multicoloured”. Secondly we propose methods using these metrics either alone or combined to classify whole-scene images into five categories of appearance: strong, pastel, dark, pale and multicoloured. Experiments show positive results and that the global colour histogram is actually useful and can be used for whole-scene colour appearance classification. We have also conducted a small-scale human evaluation test on whole-scene colour appearance. The results show, with suitable threshold settings, the proposed methods can describe the whole-scene colour appearance of images close to human classification. The descriptors were tested on thousands of images from various scenes: paintings, natural scenes, objects, photographs and documents. The colour appearance classifications are being integrated into an image browsing system which allows them to also be used to refine browsing.
منابع مشابه
Embedded colour image coding for content-based retrieval
We present an image coding method explicitly designed for easy content access, i.e., content-based image retrieval. Based on a number of well-studied conventional image coding methods, namely segmentation-based image coding (SBIC), vector quantization (VQ), and a recently developed coloured pattern appearance model (CPAM), we have developed an image coding method with a compressed stream from w...
متن کاملA Novel Method for Content Base Image Retrieval Using Combination of Local and Global Features
Content-based image retrieval (CBIR) has been an active research topic in the last decade. In this paper we proposed an image retrieval method using global and local features. Firstly, for local features extraction, SURF algorithm produces a set of interest points for each image and a set of 64-dimensional descriptors for each interest points and then to use Bag of Visual Words model, a cluster...
متن کاملComparative Study of Various Texture Based Approaches and Similarity Measurement Approaches in Cbir
Texture features are important factor in content based image retrieval. Texture descriptors are important factor in grey scale images, but due to advancements in colour image processing textures descriptors are developed a major factor for colour space images. In this paper various colour and grey scale based texture features have been discussed that can be used for extraction of texture histog...
متن کاملA Novel Method for Content Base Image Retrieval Using Combination of Local and Global Features
Content-based image retrieval (CBIR) has been an active research topic in the last decade. In this paper we proposed an image retrieval method using global and local features. Firstly, for local features extraction, SURF algorithm produces a set of interest points for each image and a set of 64-dimensional descriptors for each interest points and then to use Bag of Visual Words model, a cluster...
متن کاملCompressing histogram representations for automatic colour photo categorization
Organizing images into semantic categories can be very useful for searching and browsing through large image repositories. In this work, we use machine learning to associate low level colour representations of digital colour photos with their high level semantic categories. We investigate the redundancy and performance of a number of histogram-based colour image content representations in the c...
متن کامل