Malay Kishore Dutta

An adaptive threshold based image processing technique for improved glaucoma detection and classification

Glaucoma is an optic neuropathy which is one of the main causes of permanent blindness worldwide. This paper presents an automatic image processing based method for detection of glaucoma from the digital fundus images. In this proposed work, the discriminatory parameters of glaucoma infection, such as cup to disc ratio (CDR), neuro retinal rim (NRR) area and blood vessels in different regions of the optic disc has been used as features and fed as inputs to learning algorithms for glaucoma diagnosis. These features which have discriminatory changes with the occurrence of glaucoma are strategically used for training the classifiers to improve the accuracy of identification. The segmentation of optic disc and cup based on adaptive threshold of the pixel intensities lying in the optic nerve head region. Unlike existing methods the proposed algorithm is based on an adaptive threshold that uses local features from the fundus image for segmentation of optic cup and optic disc making it invariant to the quality of the image and noise content which may find wider acceptability. The experimental results indicate that such features are more significant in comparison to the statistical or textural features as considered in existing works. The proposed work achieves an accuracy of 94.11% with a sensitivity of 100%. A comparison of the proposed work with the existing methods indicates that the proposed approach has improved accuracy of classification glaucoma from a digital fundus which may be considered clinically significant.

Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image

Glaucoma is a disease of the retina which is one of the most common causes of permanent blindness worldwide. This paper presents an automatic image processing based method for glaucoma diagnosis from the digital fundus image. In this paper wavelet feature extraction has been followed by optimized genetic feature selection combined with several learning algorithms and various parameter settings. Unlike the existing research works where the features are considered from the complete fundus or a sub image of the fundus, this work is based on feature extraction from the segmented and blood vessel removed optic disc to improve the accuracy of identification. The experimental results presented in this paper indicate that the wavelet features of the segmented optic disc image are clinically more significant in comparison to features of the whole or sub fundus image in the detection of glaucoma from fundus image. Accuracy of glaucoma identification achieved in this work is 94.7% and a comparison with existing methods of glaucoma detection from fundus image indicates that the proposed approach has improved accuracy of classification.

An adaptive threshold based algorithm for optic disc and cup segmentation in fundus images

This paper presents an image processing technique for segmentation of optic disc and cup based on adaptive thresholding using features from the image. The proposed algorithm uses the features obtained from the image, such as mean and standard deviation, to remove information from the red and green channel of a fundus image and obtain an image which contains only the optic nerve head region in both the channels. The optic disc is segmented from the red channel and optic cup from the green channel respectively. The threshold is determined from the smoothed histogram of the preprocessed image. The results of the proposed algorithm are compared with the images that are marked by doctors. The accuracy of the algorithm is good and is computationally very fast. The proposed method can be used for screening purpose.

Biometric Based Unique Key Generation for Authentic Audio Watermarking

This paper proposes a method of generating pseudorandom number sequences based on biometric templates of iris image. These sequences are found to be unique in nature. Such sequences can be stored in a database for distinct identification of the extracted keys and they can act as secret keys for audio watermarking with a stamp of ownership unlike arbitrary pseudorandom number sequences and chaotic sequences. Correlation scores achieved under signal processing attacks is more than 0.9 that is significant for identification.

Classification of glaucoma based on texture features using neural networks

Glaucoma is the most common cause of blindness and it affects most of the ageing society and this occurs due to pressure increases in the optic nerve which damages the optic nerve. This paper is an attempt to study and analyze the texture features of the Fundus image and its variations when the Fundus image is infected with glaucoma. The texture features extracted are localized around the optic cup which gives clear results for the purpose of distinct identification and classification. The classification method proposed is use of neural network classifier with the help of texture feature extraction of the localized area of the optic cup of the fundus images. The classification method gives high level of accuracy based on the different test-train ratios. The experimental results are encouraging indicating an accuracy of above 90% accuracy in classification.

A perceptible watermarking algorithm for audio signals

This paper proposes an unconventional method for removable audible watermarking system based on the requirements of a promising application .Given an audio file, the system makes some part of file available for preview and perceptual watermarking on the remaining portion. The watermark is embedded into selected DCT coefficients of host audio signal so that the signal to noise ratio is maintained at a level which is audibly annoying to human auditory system. An issue that arises here is generating huge number of copies of the audio file which are audibly similar and numerically different. Once the audio file is decoded using the secret key a new watermark is embedded in the audio that is perceptually transparent to the human auditory system. Hence this double watermarking i.e. imperceptible and perceptible watermarking provides a novel prototype for digital right management control. The subjective quality tests and robustness tests indicate that the audio quality is excellent and is robust to signal processing attacks.

An adaptive robust watermarking algorithm for audio signals using SVD

This paper proposes an efficient watermarking algorithm which embeds watermark data adaptively in the audio signal. The algorithm embeds the watermark in the host audio signal in such a way that the degree of embedding (DOE) is adaptive in nature and is chosen in a justified manner according to the localized content of the audio. The watermark embedding regions are selectively chosen in the high energy regions of the audio signal which make the embedding process robust to synchronization attacks. Synchronization codes are added along with the watermark in the wavelet domain and hence the embedded data can be subjected to self synchronization and the synchronization code can be used as a check to combat false alarm that results from data modification due to watermark embedding. The watermark is embedded by quantization of the singular value decompositions in the wavelet domain which makes the process perceptually transparent. The experimental results suggest that the proposed algorithm maintains a good perceptual quality of the audio signal and maintains good robustness against signal processing attacks. Comparative analysis indicates that the proposed algorithm of adaptive DOE has superior performance in comparison to existing uniform DOE.

A blind audio watermarking algorithm robust against synchronization attacks

Time Scale Modification, Mp3 Compression and random cropping are challenging problems in watermarking of audio signals. To overcome these signal processing attacks, an imperceptible, blind and secure audio watermarking algorithm is presented in this paper. The proposed algorithm calculates the watermark embedding regions (WER) based on the audio localized content analysis and then embeds watermark data in these selected regions. The selection of region of embedding is done by finding regions which are relatively invariant to synchronization attacks. This makes the embedded watermark robust to time stretching or compressing attacks. Multiresolution decomposition of the signal using wavelet domain is used in this paper for watermarking. Experimental results validate that the algorithm is robust to Time Scale Modification, Mp3 Compression and other audio signal processing attacks and maintains perceptual transparency to an accepted level with SNR above 30dB.

Blood vessel inpainting based technique for efficient localization and segmentation of optic disc in digital fundus images

Abstract The Optic disc (OD) nerve head region in general and OD center coordinates in particular form basis for study and analysis of various eye pathologies. The shape, contour and size of OD is vital in classification and grading of retinal diseases like glaucoma. There is a need to develop fast and efficient algorithms for large scale retinal disease screening. With this in mind, this paper present a novel framework for fast and fully automatic detection of OD and its accurate segmentation in digital fundus images. The methodology involves optic disc center localization followed by removal of vascular structure by accurate inpainting of blood vessels in the optic disc region. An adaptive threshold based Region Growing technique is then employed for reliable segmentation of fundus images. The proposed technique achieved significant results when tested on standard test databases like MESSIDOR and DRIVE with average overlapping ratio of 89% and 87%, respectively. Validation experiments were done on a labeled dataset containing healthy and pathological images obtained from a local eye hospital achieving an appreciable 91% average OD segmentation accuracy.

An efficient and lossless fingerprint encryption algorithm using Henon map & Arnold transformation

In this paper two stage biometric data protection scheme is being proposed using permutation and substitution mechanism of the chaotic theory which is lossless in nature. Arnold transformation and Henon map is used to design an efficient encryption system. The encryption method is aimed at generating an encrypted image that will have statistical properties completely dissimilar from the original image analysis which will make it difficult for any intruder to decrypt the image. The performance of the method has been experimentally analyzed using statistical analysis and correlation based methods. Correlation coefficient analysis is done to evaluate the behavior of pixels in horizontal and vertical directions and the results are found to be encouraging. This protection scheme provides the ability to encrypt the data and secure it from unauthorized users. Upon decryption the data is completely recovered making this scheme a lossless and efficient method of biometric data security.