Images in their uncompressed form require large amount of storage capacity and uncompresses data needs large transmission bandwidth for the transmission. Image compression technique is used to reduce the storage requirement per image, while maintaining image quality. The proposed method investigates biometric image compression using Gaussian Pyramid Compression (GPC) in which the performance is observed down to 0.23 bits/pixel attributed to noise reduction without a significant loss of texture. Objective measures were used such as Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE) and Bit Rate (BR) to evaluate the image quality for both gray and RGB biometric images. The comparisons of Gaussian Pyramid compression technique applied to .jpg, .bmp and .png images.

http://www.ijcsi.org/papers/IJCSI-11-3-1-77-82.pdf

Efficiency of Gaussian Pyramid Compression Technique for Biometric Images

With increasing usage of fingerprints as an important biometric data, the need to compress the large fingerprint databases has become essential. The most recommended compression algorithm, even by standards, is JPEG2K. But at high compression rates, this algorithm is ineffective. In this paper, a model is proposed which is based on parallel lines with same orientations, arbitrary widths and same gray level values located on rectangle with constant gray level value as background. We refer to this algorithm as Parallel Stroked Multi Line (PSML). By using Adaptive Geometrical Wavelet and employing PSML, a compression algorithm is developed. This compression algorithm can preserve fingerprint structure and minutiae. The exact algorithm of computing the PSML model take exponential time. However, we have proposed an alternative approximation algorithm, which reduces the time complexity to $O(n^3)$. The proposed PSML alg. has significant advantage over Wedgelets Transform in PSNR value and visual quality in compressed images. The proposed method, despite the lower PSNR values than JPEG2K algorithm in common range of compression rates, in all compression rates have nearly equal or greater advantage over JPEG2K when used by Automatic Fingerprint Identification Systems (AFIS). At high compression rates, according to PSNR values, mean EER rate and visual quality, the encoded images with JPEG2K can not be identified from each other after compression. But, images encoded by the PSML alg. retained the sufficient information to maintain fingerprint identification performances similar to the ones obtained by raw images without compression. One the U.are.U 400 database, the mean EER rate for uncompressed images is 4.54%, while at 267:1 compression ratio, this value becomes 49.41% and 6.22% for JPEG2K and PSML, respectively. This result shows a significant improvement over the standard JPEG2K algorithm.

Parallel Stroked Multi Line: a model-based method for compressing large fingerprint databases.

Biometric identification systems are in use for last many years for the purpose of personal identification, uncompressed graphics, audio and video data require considerable storage capacity and transmission bandwidth dealing with such enormous amount of information can often present difficulties. As per my literature survey, there is no such method that uses compressive sensing and adaptive learning dictionary to compress image along with neural network to estimate the results. In the given algorithm, a dictionary of predefined fingerprint patches is constructed which is than quantized and encoded.

/pdf/fingerprint-compression-using-sparse-representation-y907p5j792.pdf

Fingerprint Compression using Sparse Representation

Modified Set Partitioning in Hierarchical Tree with Run Length Encoding is a new framework proposed for fingerprint image compression. The Proposed method is better because more number of images related to the fingerprint image are retrieved. Experiments on an image database of grayscale bitmap images show that the proposed technique performs well in compression and decompression. We use Peak Signal to noise ratio [3] and Mean Square Error [3] to compute the picture quality of fingerprint images.

Mansi Kambli

Papers

Fingerprint Image Compression