Poorna B, Easwarakumar K S
Department of Computer Applications, Dr. M.G.R. Engineering College, Maduravoyal, Chennai 602 102, India.
Int J Neural Syst. 2003 Aug;13(4):263-71. doi: 10.1142/S0129065703001583.
An efficient method for fingerprint searching using recurrent autoassociative memory is proposed. This algorithm uses recurrent autoassociative memory, which uses a connectivity matrix to find if the pattern being searched is already stored in the database. The advantage of this memory is that a big database is to be searched only if there is a matching pattern. Fingerprint comparison is usually based on minutiae matching, and its efficiency depends on the extraction of minutiae. This process may reduce the speed, when large amount of data is involved. So, in the proposed method, a simple approach has been adopted, wherein first determines the closely matched fingerprint images, and then determines the minutiae of only those images for finding the more appropriate one. The gray level value of pixels along with its neighboring ones are considered for the extraction of minutiae, which is more easier than using ridge information. This approach is best suitable when database size is large.
提出了一种使用递归自联想记忆进行指纹搜索的有效方法。该算法使用递归自联想记忆，它通过一个连接矩阵来判断正在搜索的模式是否已存储在数据库中。这种记忆的优点是只有在存在匹配模式时才搜索大型数据库。指纹比对通常基于细节特征匹配，其效率取决于细节特征的提取。当涉及大量数据时，这个过程可能会降低速度。因此，在所提出的方法中，采用了一种简单的方法，即首先确定紧密匹配的指纹图像，然后仅确定那些图像的细节特征以找到更合适的一个。在提取细节特征时考虑像素及其相邻像素的灰度值，这比使用脊线信息要容易得多。当数据库规模较大时，这种方法最为适用。
