Miroslaw Bober

Bio: Miroslaw Bober is an academic researcher from University of Surrey. The author has contributed to research in topics: Motion estimation & Object (computer science). The author has an hindex of 25, co-authored 202 publications receiving 2497 citations. Previous affiliations of Miroslaw Bober include Mitsubishi Electric & Mitsubishi.

MPEG-7 visual shape descriptors

Abstract: This paper describes techniques and tools for shape representation and matching, developed in the context of MPEG-7 standardization. The application domains for each descriptor are considered, and the contour-based shape descriptor is presented in some detail. Example applications are also shown.

Method and apparatus for video navigation

Abstract: A method of deriving a representation of a video sequence comprises deriving metadata expressing at least one temporal characteristic of a frame or group of frames, and one or both of metadata expressing at least one content-based characteristic of a frame or group of frames and relational metadata expressing relationships between at least one content-based characteristic of a frame or group of frames and at least one other frame or group of frames, and associating said metadata and/or relational metadata with the respective frame or group of frames.

Semantic segmentation of images exploiting DCT based features and random forest

Abstract: This paper presents an approach for generating class-specific image segmentation. We introduce two novel features that use the quantized data of the Discrete Cosine Transform (DCT) in a Semantic Texton Forest based framework (STF), by combining together colour and texture information for semantic segmentation purpose. The combination of multiple features in a segmentation system is not a straightforward process. The proposed system is designed to exploit complementary features in a computationally efficient manner. Our DCT based features describe complex textures represented in the frequency domain and not just simple textures obtained using differences between intensity of pixels as in the classic STF approach. Differently than existing methods (e.g., filter bank) just a limited amount of resources is required. The proposed method has been tested on two popular databases: CamVid and MSRC-v2. Comparison with respect to recent state-of-the-art methods shows improvement in terms of semantic segmentation accuracy. HighlightsA method for semantic image segmentation based on random forests.Novel texture features based on Discrete Cosine Transform to describe image regions.The method uses a limited amount of resources and works in realtime.The approach shows good performance overcoming other state of the art.The system obtains a better accuracy on small classes (i.e., Pedestrians).

Method and apparatus for searching for and retrieving colour images

Abstract: A method of searching for an image or images corresponding to a query comprises comparing a colour descriptor of the query with stored colour descriptors of each of a collection of reference images, and deriving a matching value indicating the degree of matching between the query and a reference image using the query and reference descriptors, and classifying the reference images by said matching value, each colour descriptor including an indication of one or more dominant colours within the corresponding query or reference image, wherein at least one of the query descriptor and a reference descriptor indicates two or more dominant colours, so that the corresponding descriptor comprises a plurality of subdescriptors, each subdescriptor relating to at least one dominant colour in the corresponding query or reference image, the method comprising deriving the matching value by considering a subset of the dominant colours in either the query or reference descriptor or both using a subdescriptor of either the query descriptor or the reference descriptor or both.

Robust image registration

Abstract: A method of estimating a transformation between a pair of images, comprises estimating local transformations for a plurality of regions of the images to derive a set of estimated transformations, and selecting a subset of said estimated local transformations as estimated global transformations for the image.

The Self-Organizing Map

Abstract: An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

Iterative Quantization: A Procrustean Approach to Learning Binary Codes for Large-Scale Image Retrieval

Abstract: This paper addresses the problem of learning similarity-preserving binary codes for efficient similarity search in large-scale image collections. We formulate this problem in terms of finding a rotation of zero-centered data so as to minimize the quantization error of mapping this data to the vertices of a zero-centered binary hypercube, and propose a simple and efficient alternating minimization algorithm to accomplish this task. This algorithm, dubbed iterative quantization (ITQ), has connections to multiclass spectral clustering and to the orthogonal Procrustes problem, and it can be used both with unsupervised data embeddings such as PCA and supervised embeddings such as canonical correlation analysis (CCA). The resulting binary codes significantly outperform several other state-of-the-art methods. We also show that further performance improvements can result from transforming the data with a nonlinear kernel mapping prior to PCA or CCA. Finally, we demonstrate an application of ITQ to learning binary attributes or "classemes" on the ImageNet data set.