Recognizing symbol is the first step in using a topographic map. Despite the prerequisite for extraction of information from topographic map, automated understanding of symbols is a challenging task. The objective of ...
详细信息
ISBN:
(纸本)9781467360999;9781467361002
Recognizing symbol is the first step in using a topographic map. Despite the prerequisite for extraction of information from topographic map, automated understanding of symbols is a challenging task. The objective of this paper is to explain the development of a system for automatic understanding of symbols from the Indian topographic map. The system has been developed making use of shape analysis method in which complex valued chain coding has been used for representation of the exterior boundary of the shape of the symbol. Fourier discrete transform and Auto-correlation function have been used to define shape descriptors. Classification and recognition have been implemented through template matching method and Similarity measures. The system is trained with 150 samples of each of 20 types of symbols from National digital topographic database (NTDB) for OSM of Indian topographic maps. The developed system is tested for 200 samples of each type of symbol from NTDB. It is found that 84.68% of symbols are understood correctly by the developed system. However, there are some inherent limitations in understanding the symbols from an actual map.
The existing image compression standards like JPEG and JPEG 2000, compress the whole image as a single frame. This makes the system simple but inefficient. The problem is acute for applications where lossless compress...
详细信息
ISBN:
(纸本)081945284X
The existing image compression standards like JPEG and JPEG 2000, compress the whole image as a single frame. This makes the system simple but inefficient. The problem is acute for applications where lossless compression is mandatory viz. medical image compression. If the spatial characteristics of the image are considered, it can give rise to a more efficient coding scheme. For example, CT reconstructed images have uniform background outside the field of view (FOV). Even the portion within the FOV can be divided as anatomically relevant and irrelevant parts. They have distinctly different statistics. Hence coding them separately will result in more efficient compression. Segmentation is done based on thresholding and shape information is stored using 8-connected differential chain code. Simple I-D DPCM is used as the prediction scheme. The experiments show that the 1st order entropies of images fall by more than 11% when each segment is coded separately. For simplicity and speed of decoding Huffman code is chosen for entropy coding. Segment based coding will have an overhead of one table per segment but the overhead is minimal. Lossless compression of image based on segmentation resulted in reduction of bit rate by 7%-9% compared to lossless compression of whole image as a single frame by the same prediction coder. Segmentation based scheme also has the advantage of natural ROI based progressive decoding. If it is allowed to delete the diagnostically irrelevant portions, the bit budget can go down as much as 40%. This concept can be extended to other modalities.
We present a new approach based on the Slope chain Code to determine whether a curve is rotational symmetrical and its order of symmetry. The proposed approach works for open and closed perfectly symmetrical or quasi-...
详细信息
We present a new approach based on the Slope chain Code to determine whether a curve is rotational symmetrical and its order of symmetry. The proposed approach works for open and closed perfectly symmetrical or quasi-symmetrical 2D curves. Simple operations on the SCC and its invariant properties are central to our methodology. To evaluate the proposed methodology, we use 1400 curves from a public database. For the symmetrical/asymmetrical classification task, a recall (R) of 0.86, a balanced accuracy (BA) of 0.92, and a precision (P) of 0.87 were obtained. For the quasi-symmetrical/quasi-asymmetrical classification task, R=0.77, BA=0.83, and P=0.70 were obtained. For the order of rotational symmetry detection task, the following performance was achieved: R=0.97, BA=0.98, and P=0.95 for a symmetrical set of curves, and R=0.98, BA=0.98, and P=0.90 for a quasi-symmetrical set of curves. We conclude our presentation demonstrating the usefulness of our methodology with three practical applications (C) 2020 Elsevier Ltd. All rights reserved.
暂无评论