Search

Diabetic retinopathy (DR), which affects the blood vessels of the human retina, is considered to be the most serious complication prevalent among diabetic patients. If detected successfully at an early stage, the ophthalmologist would be able to treat the patients by advanced laser treatment to prevent total blindness. In this study, a technique based on morphological image processing and fuzzy logic to detect hard exudates from DR retinal images is explored. The proposed technique is to classify the eye by using a neural network approach (classifier) to predict whether it is affected or not. Here, a classifier is added before the fuzzy logic. This fuzzy will tell how much and where it is affected. The proposed technique will tell whether the eye is abnormal or normal.

It is one of the most vital symptoms of DR (diabetic retinopathy) called hard exudates (HE), which are the leakage of cellular debris and lipoprotein from damaged blood vessels of retina. The vision loss is avoided if the detection of HE in the beginning times. Therefore, a novel method is proposed to detect hard exudates automatically. Previously, for exudate prediction supervised and unsupervised methods have been used. Fault detection of hard exudates, miss classification rate will affect these models because of the characteristics like, similarities with other components in the retinal image and intra variations. For that, the retinal fundus images has been used as input. Then these images are pre-processed with some pre-processing algorithms like image enhancement, equalization of histogram to improve the proposed system performance. Total image data files are divided to training and testing datasets. Features are extracted for training and testing using feature extraction algorithm individually. Then classifier algorithm predicts whether the hard exudate is proliferative or non-proliferative. We obtained accuracy of 99.34% using our proposed methods on public datasets like DIARETDB1 and DRIVE.

Eyes are the organs of the visual system. The eyes are affected by eye diseases causing loss of vision. Retinitis Pigmentosa is a genetic condition which is passed down to families and it varies from person to person. Segmentation (Automatic) of external retinal layers is challenging because of the resolution of the human eye. This paper proposes a technique to classify the external retinal layers by means of KNN. It helps doctors to plan on further treatment. To segment the external layers in the retina by applying different preprocessing steps. To detect the region of interest(outer retina) the pre-processing step is performed. Second, few Framework parameters of the outer retina are calculated by fitting the candidate models. To select the Framework supported by the data Framework resolution technique is required by model selection. The detected layers are assigned by the labels (layer identification). Finally, classification by (KNN) to decide whether or not the eye's is in normal or in abnormal condition.

Computer vision is the process of acquisition, processing and analysis of real world scenes in order to take different decisions based on applications. Computer vision systems are electronic replacement of human visual ability. Applications of computer vision systems are wide. This paper reviews the progress of computer vision in various fields of automatic inspection systems. Since conventional defect detection systems are prone to many disadvantages, computer vision with its efficiency and cost effectiveness is emerging as the latest revolution of technology. At the end of this paper, some advantages and disadvantages of computer vision and a suitable area and method for further research are also discussed.

Retinal fundus image morphology indicates diseases like diabetic retinopathy and glaucoma like diseases. Blood vessel features of the retinal image allow ophthalmologist to perform retinal disease evaluation. Presence of lesions in the fundus image is initial sign of diabetic retinopathy. Preprocessing technique is mainly used to remove unwanted noises and it enhances some image features. Different types of pre-processing techniques are used for image processing. This paper represents the comparison of different methods used for pre-processing in retinal fundus image.

To segment an image in thresholding method, a fixed threshold is not suitable if the background is rough here, we propose a new robust adaptive thresholding method using TKFCM. The method requires only one parameter to be selected and the adaptive threshold surface can be found automatically from the original image. A Robust adaptive thresholding scheme using adaptive tracking and morphological filtering. TKFCM algorithm computes the fuzzy membership values for each pixel. On the source of TKFCM the edge indicator function was redefined. Using the edge indicator function of an image was performed to extract the boundaries of objects on the origin of the pre-segmentation. Therefore, the proposed method is computationally efficient. The efficiency and accuracy of the algorithm is demonstrated. The above process of segmentation showed a considerable improvement in the evolution of the level set function. Our method is good for detecting large and small images concurrently. It is also efficient to denoise and enhance the responses of images with low local contrast can be detected.

Using thresholding method to segment an image, a fixed threshold is not suitable if the background is rough here, we propose a new adaptive thresholding method using KFCM. The method requires only one parameter to be selected and the adaptive threshold surface can be found automatically from the original image. An adaptive thresholding scheme using adaptive tracking and morphological filtering. KFCM algorithm computes the fuzzy membership values for each pixel. Our method is good for detecting large and small images concurrently. It is also efficient to denoise and enhance the responses of images with low local contrast can be detected. The efficiency and accuracy of the algorithm is demonstrated by the experiments on the MR brain images.

Using thresholding method to segment an image, a fixed threshold is not suitable if the background is rough Here, we propose a new adaptive thresholding method using FCM. The method requires only one parameter to be selected and the adaptive threshold surface can be found automatically from the original image.An adaptive thresholding scheme using adaptive tracking and morphological filtering. FCM algorithm computes the fuzzy membership values for each pixel. Our method is good for detecting large and small images concurrently. It is also efficient to denoise and enhance the responses of images with low local contrast can be detected. The efficiency and accuracy of the algorithm is demonstrated by the experiments on the MR brain images.