A novel adaptive morphological approach for degraded character image segmentation

@article{citeulike:820302, abstract = {This work proposes a novel adaptive approach for character segmentation and feature vector extraction from seriously degraded images. An algorithm based on the histogram automatically detects fragments and merges these fragments before segmenting the fragmented characters. A morphological thickening algorithm automatically locates reference lines for separating the overlapped characters. A morphological thinning algorithm and the segmentation cost calculation automatically determine the baseline for segmenting the connected characters. Basically, our approach can detect fragmented, overlapped, or connected character and adaptively apply for one of three algorithms without manual fine-tuning. Seriously degraded images as license plate images taken from real world are used in the experiments to evaluate the robustness, the flexibility and the effectiveness of our approach. The system approach output data as feature vectors keep useful information more accurately to be used as input data in an automatic pattern recognition system.}, author = {Nomura, Shigueo and Yamanaka, Keiji and Katai, Osamu and Kawakami, Hiroshi and Shiose, Takayuki}, citeulike-article-id = {820302}, doi = {10.1016/j.patcog.2005.01.026}, journal = {Pattern Recognition}, keywords = {character, degraded, segmentation}, month = {November}, number = {11}, pages = {1961--1975}, posted-at = {2006-08-29 02:31:04}, priority = {4}, title = {A novel adaptive morphological approach for degraded character image segmentation}, url = {http://dx.doi.org/10.1016/j.patcog.2005.01.026}, volume = {38}, year = {2005} }

TY - JOUR ID - citeulike:820302 L3 - citeulike-article-id:820302 N2 - This work proposes a novel adaptive approach for character segmentation and feature vector extraction from seriously degraded images. An algorithm based on the histogram automatically detects fragments and merges these fragments before segmenting the fragmented characters. A morphological thickening algorithm automatically locates reference lines for separating the overlapped characters. A morphological thinning algorithm and the segmentation cost calculation automatically determine the baseline for segmenting the connected characters. Basically, our approach can detect fragmented, overlapped, or connected character and adaptively apply for one of three algorithms without manual fine-tuning. Seriously degraded images as license plate images taken from real world are used in the experiments to evaluate the robustness, the flexibility and the effectiveness of our approach. The system approach output data as feature vectors keep useful information more accurately to be used as input data in an automatic pattern recognition system. IS - 11 JF - Pattern Recognition EP - 1975 TI - A novel adaptive morphological approach for degraded character image segmentation VL - 38 SP - 1961 KW - character KW - degraded KW - segmentation AU - Nomura, Shigueo AU - Yamanaka, Keiji AU - Katai, Osamu AU - Kawakami, Hiroshi AU - Shiose, Takayuki PY - 2005/11// UR - http://dx.doi.org/10.1016/j.patcog.2005.01.026 ER -