In this work we analyze the contribution of preprocessing steps for Latin handwriting recognition. A preprocessing pipeline based on geometric heuristics and image statistics is used. this pipeline is applied to Frenc...
详细信息
ISBN:
(纸本)9780769547749;9781467322621
In this work we analyze the contribution of preprocessing steps for Latin handwriting recognition. A preprocessing pipeline based on geometric heuristics and image statistics is used. this pipeline is applied to French and English handwriting recognition in an HMM based framework. Results show that preprocessing improves recognition performance for the two tasks. the Maximum Likelihood (ML)-trained HMM system reaches a competitive WER of 16.7% and outperforms many sophisticated systems for the French handwriting recognition task. the results for English handwriting are comparable to other ML-trained HMM recognizers. Using MLP preprocessing a WER of 35.3% is achieved.
the fundamental matrix (FM) represents the perspective transform between two or more uncalibrated images of a stationary scene, and is traditionally estimated based on 2-parameter point-to-point correspondences betwee...
详细信息
ISBN:
(纸本)0769525210
the fundamental matrix (FM) represents the perspective transform between two or more uncalibrated images of a stationary scene, and is traditionally estimated based on 2-parameter point-to-point correspondences between image pairs. Recent invariant correspondence techniques however, provide robust correspondences in terms of 4 to 6-parameter invariant regions. Such correspondences contain important information regarding scene geometry, information which is lost in FM estimation techniques based solely on 2-parameter point translation. In this article, we present a method of incorporating this additional information into point-based FM estimation routines, entitled TIP (transfer of invariant parameters). the TIP method transforms invariant correspondence parameters into additional point correspondences, which can be used with FM estimation routines. Experimentation shows that the TIP methods result in more robust FM estimates in the case of sparse correspondence, and allows estimation based on as few as 3 correspondences in the case of affine-invariant features.
In this paper a novel analysis of space-time volume of spherical projection image is presented. So far space-time analyses have been extensively conducted for various purposes, i.e. 3-D reconstruction, estimation of c...
详细信息
ISBN:
(纸本)0769525210
In this paper a novel analysis of space-time volume of spherical projection image is presented. So far space-time analyses have been extensively conducted for various purposes, i.e. 3-D reconstruction, estimation of camera motion and novel view synthesis and most of them consider only a planer projection and a single camera. In contrast, we conducted analysis on spherical projection for multiple cameras. Since spherical projection does not change its appearance in relation to rotation around the origin of the sphere, extrinsic camera parameters and synchronous parameters of multiple video cameras can be simultaneously estimated by registering multiple space-time volumes of spherical projection, which can be easily achieved by block-matching technique. By using the parameters, multiple video images can be successfully integrated into single omni-directional images without distortions.
Two HMM-based threshold models are suggested for recognition and incremental learning of scenario-oriented human behavior patterns. One is the expected behavior threshold model to discriminate if a monitored behavior ...
详细信息
ISBN:
(纸本)9781450305617
Two HMM-based threshold models are suggested for recognition and incremental learning of scenario-oriented human behavior patterns. One is the expected behavior threshold model to discriminate if a monitored behavior pattern is normal or not. the other model is the registered behavior threshold model to detect whether such behavior pattern is already learned. If a behavior patten is detected as a new one, an HMM is generated to represent the pattern, and then the HMM is used to update behavior clusters by hierarchical clustering process.
暂无评论