In this poster, we present an approach to contex-tualized semantic image annotation as an optimization problem. Ontologies are used to capture general and contextual knowledge of the domain considered, and a genetic a...
详细信息
In this poster, we present an approach to contex-tualized semantic image annotation as an optimization problem. Ontologies are used to capture general and contextual knowledge of the domain considered, and a genetic algorithm is applied to realize the final annotation. Experiments with images from the beach vacation domain demonstrate the performance of the proposed approach and illustrate the added value of utilizing contextual information.
Nowadays, the huge non-indexing quantities of image archives (especially document images) require the development of intelligent tools for their retrieval with convenience comparable of the texts search engines. The p...
详细信息
Nowadays, the huge non-indexing quantities of image archives (especially document images) require the development of intelligent tools for their retrieval with convenience comparable of the texts search engines. The proposed technique addresses the document retrieval problem by a word matching procedure. It performs matching directly in the images bypassing OCR and using word-images as queries. It is constituted of two different parts: The offline and the online operation. In the offline operation, the archive of document images is examined and the results are stored in a database. The online operation consists of the Web interface, the creation of the word's image and finally, the matching stage. The proposed matching process it can be described shortly as a two-threshold rating system. Finally, the proposed system has been build and it can be found in at the Web address: http://***/irs2.
A new technique for solving jigsaw puzzles is proposed, which takes advantage of both geometrical and color features. It is considered that an image is being divided into a number of pieces (sub-images). The proposed ...
详细信息
A new technique for solving jigsaw puzzles is proposed, which takes advantage of both geometrical and color features. It is considered that an image is being divided into a number of pieces (sub-images). The proposed technique is based on extraction of a set of boundary characteristic points and on a Kohonen self-organized feature map (KSOFM) color reduction technique. For each characteristic point a set of color and geometrical features are extracted. The technique compares these sets of features and decides whether two sub-images match or not. When a matching pair has been found, a corrective procedure is applied in order for these sub-images to fit exactly. Next, the proposed technique creates a new sub-image, which consists of the two matched sub-images. The whole matching procedure is being repeated until only one sub-image remains or no more matching sub-images can be found.
A new method for hand gesture recognition is proposed which is based on an innovative self-growing and self-organized neural gas (SGONG) network. Initially, the region of the hand is detected by using a color segmenta...
详细信息
A new method for hand gesture recognition is proposed which is based on an innovative self-growing and self-organized neural gas (SGONG) network. Initially, the region of the hand is detected by using a color segmentation technique that depends on a skin-color distribution map. Then, the SGONG network is applied on the segmented hand so as to approach its topology. Based on the output grid of neurons, palm geometric characteristics are obtained which in accordance with powerful finger features allow the identification of the raised fingers. Finally, the hand gesture recognition is accomplished through a probability-based classification method.
The MISP processor is a programmable media processor which supports multi-issuing, multi-threading and stream processing techniques. MISP executes applications that have been mapped to the stream programming model. Th...
详细信息
The MISP processor is a programmable media processor which supports multi-issuing, multi-threading and stream processing techniques. MISP executes applications that have been mapped to the stream programming model. The stream model decomposes applications into a set of computation kernels that operate on data streams. This mapping exposes the inherent locality and parallelisms in media applications. MISP exploits thread level (TLP), data level (DLP), sub-word (SP) and instruction level (ILP) parallelisms inherent in media applications. Full simulator of MISP has been implemented and several media workloads composed of EEMBC benchmarks have been applied. Also we applied test programs on imagine stream processor. The simulation results show MISP gains IPC of more than 2.08 times and performance of more than 1.86 times over imagine. The synthesis results show area overhead per thread addition in MISP is about 7% without changing clock frequency
An efficient algorithm using maximum a posteriori-Markov random field (MAP-MRF) based approach for recovering a high-resolution image from multiple sub-pixel shifted low-resolution images is proposed. The algorithm ca...
详细信息
An efficient algorithm using maximum a posteriori-Markov random field (MAP-MRF) based approach for recovering a high-resolution image from multiple sub-pixel shifted low-resolution images is proposed. The algorithm can be used for super-resolution of both space-invariant and space-variant blurred images. We prove an important theorem that the posterior is also Markov and derive the exact posterior neighborhood structure in the presence of warping, blurring and down-sampling operations. The posterior being Markov enables us to perform all matrix operations as local image domain operations thereby resulting in a considerable speedup. Experimental results are given to demonstrate the effectiveness of our method
Shape from focus (SFF) method determines the degree of focus in a sequence of observations to estimate the shape of a 3-D object. Existing SFF algorithms use an ad hoc interpolation strategy to account for the error d...
详细信息
ISBN:
(纸本)0769525210
Shape from focus (SFF) method determines the degree of focus in a sequence of observations to estimate the shape of a 3-D object. Existing SFF algorithms use an ad hoc interpolation strategy to account for the error due to the finite step-size by which the translational table is moved while capturing the images. We propose an improved SFF method that uses relative defocus blur derived from actual image data to arrive at the final estimates of the shape of the object. A space-variant image restoration scheme is also proposed to obtain a focused image of the 3-D object. The shape estimates as well as the quality of the restored image using the proposed method are superior to that of traditional SFF
We present automatic target recognition (ATR) model based on principles of biological vision systems. The model employs reinforcement learning (RL) through Dual Heuristic Programming (DHP). The performance of the repo...
详细信息
We present automatic target recognition (ATR) model based on principles of biological vision systems. The model employs reinforcement learning (RL) through Dual Heuristic Programming (DHP). The performance of the reported ATR model is compared to that of our previously reported ATR model, based on Heuristic Dynamic Programming (HDP). The HDP and DHP, known as the Adaptive Critic Designs (ACD), are neural network based implementation of Dynamic Programming (DP). The simulation shows promising results for both HDP and DHP based ATR model in presence of resolution distortion in incoming images and confirms that the DHP model is faster and more robust for our ATR system than the HDP.
暂无评论