摘要 :
In this paper, we propose a text matching method for document image retrieval without any language model. Two word images are first normalized to an appropriate size and image features are extracted using the local crowdedness met...
展开
In this paper, we propose a text matching method for document image retrieval without any language model. Two word images are first normalized to an appropriate size and image features are extracted using the local crowdedness method. Similarity between t
收起
摘要 :
In this paper, we propose a staff-line detection and removal algorithm from a music score image obtained by a digital camera. As a preprocessing technique to recognize a music score image, staff-line detection and removal should b...
展开
In this paper, we propose a staff-line detection and removal algorithm from a music score image obtained by a digital camera. As a preprocessing technique to recognize a music score image, staff-line detection and removal should be efficiently applied to the distorted images from a skew or curve. The proposed method detects staff-lines by dividing a stave according to the degree of distortion. The number of division is calculated by dividing a stave repeatedly, until an average of differences between the divided y coordinates is smaller than a threshold. Therefore, the number of division can be adaptively estimated according to the degree of distortion. For an experiment, we make various kinds of distorted images by skewing from 1° to 3° or curving. The results show that the proposed method performed well on the experiment images.
收起