Detection of diabetic retinopathy using a fusion of textural and ridgelet features of retinal images and sequential minimal optimization classifier

Diabetes is one of the most prevalent diseases in the world, which is a metabolic disorder characterized by high blood sugar. Diabetes complications are leading to Diabetic Retinopathy (DR). The early stages of DR may have either no sign or cause minor vision problems, but later stages of the disease can lead to blindness. DR diagnosis is an exceedingly difficult task because of changes in the retina during the disease stages. An automatic DR early detection method can save a patient's vision and can also support the ophthalmologists in DR screening. This paper develops a model for the diagnostics of DR. Initially, we extract and fuse the ophthalmoscopic features from the retina images based on textural gray-level features like co-occurrence, run-length matrix, as well as the coefficients of the Ridgelet Transform. Based on the retina features, the Sequential Minimal Optimization (SMO) classification is used to classify diabetic retinopathy. For performance analysis, the openly accessible retinal image datasets are used, and the findings of the experiments demonstrate the quality and efficacy of the proposed method (we achieved 98.87% sensitivity, 95.24% specificity, 97.05% accuracy on DIARETDB1 dataset, and 90.9% sensitivity, 91.0% specificity, 91.0% accuracy on KAGGLE dataset).

Secured ICA Technique on Bimodal Biometric Images Using Private Watermarking with DCT

With the discovery of paperless expensive means of internet access, network communication via social media is on the rise, which often comprises threats and distortions. Un authenticates identification may sometimes lead to ambiguities in end-user identification and misunderstandings. Therefore, proper identification of a person is a must in network communication. Image private watermarking[7][9][19] is one solution when the owner of the digital images are identified properly by embedding additional information such as a private watermark in the digital images like fingerprint and retina imperceptibly concealed inside another image. On the other hand, communication also leads to a serious surge in decompress technique on the images. This work introduces three techniques: digital watermarking, steganography, ICA[4][5][6][20][22]. Using a private watermark using the visible [9][7] and non-blind[9][19][7] technique on the photo image. Then two original fingerprints and retina images to achieve stego analysis technique to convert as a stego image. Then the stego image concealed by a watermarked photo image. Then mixing the two techniques to achieve the ICA[20][22][4][5][6] (Independent Component Analysis) for protecting data transmission. To providing compression using the IDCT (Inverse Discrete Cosine Transform) technique with the key using AES[10][9][19] (Advanced Encryption Standard) 64-bit algorithm. Implementation and to determine the utilize the JAVA platform.