• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1269-1279
• /
• 2019

In medical image analysis, segmentation is considered as a vital process since it partitions an image into coherent parts and extracts interesting objects from the image. In this paper, we consider automatic segmentations of OCT retinal images to find six layer boundaries using convolutional neural networks. Segmenting retinal images by layer boundaries is very important in diagnosing and predicting progress of eye diseases including diabetic retinopathy, glaucoma, and AMD (age-related macular degeneration). We applied well-known CNN architecture for general image segmentation, called Segnet, U-net, and CNN-S into this problem. We also proposed a shortest path-based algorithm for finding the layer boundaries from the outputs of Segnet and U-net. We analysed their performance on public OCT image data set. The experimental results show that the Segnet combined with the proposed shortest path-based boundary finding algorithm outperforms other two networks.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.1
• /
• pp.88-96
• /
• 2012

According to development of technology for media, observers try to watch the realities from images, as follows, 3D imaging has been extremely developed. 3D image gives depth in the image, observers feel in nature. Different image perception from left and right eyes make the 3D image. Anaglyph which is one of the ways to make an image of three dimensions is for obtaining an image of three dimensions by using color filter glasses. Anaglyph has a little amount of calculation and is easy to make, and it has a good point that anaglyph can be used in more wide field because it can create an image of three dimensions to the output of print like printed matter. However, the phenomenon of retinal rivalry can cause a feeling of fatigue because a difference of brightness of the left image and the right image happen. The way to reduce this problem is made by cutting down a difference of brightness. In the result, retinal rivalry can be reduced. We reduced a difference of the brightness of the left and the right image by utilizing the brightness and average of the original image to reduce retinal rivalry and we made better colors of anaglyph by using the way that we keep the hue caused by a change of brightness and supplement saturation about color distortion which is created at that time.

• International Journal of Computer Science & Network Security
• /
• v.23 no.3
• /
• pp.187-192
• /
• 2023

With development of information technology and necessity for high security, using different identification methods has become very important. Each biometric feature has its own advantages and disadvantages and choosing each of them depends on our usage. Retinal scanning is a bio scale method for identification. The retina is composed of vessels and optical disk. The vessels distribution pattern is one the remarkable retinal identification methods. In this paper, a new approach is presented for identification via retinal images using LBP and hog methods. In the proposed method, it will be tried to separate the retinal vessels accurately via machine vision techniques which will have good sustainability in rotation and size change. HOG-based or LBP-based methods or their combination can be used for separation and also HSV color space can be used too. Having extracted the features, the similarity criteria can be used for identification. The implementation of proposed method and its comparison with one of the newly-presented methods in this area shows better performance of the proposed method.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2002.08a
• /
• pp.1009-1011
• /
• 2002

We developed a Retinal Projection Display for a low vision aid. This device can be applied to a low vision whose visual sense is weak. In the device, a digital image was formed with spatial light modulator(SLM) and projected onto a retina with the Maxwellian View. The image on this display can be seen clearly without our ocular accommodation and a low vision can see it without correction of a refraction error.

• 전기의세계
• /
• v.26 no.4
• /
• pp.54-60
• /
• 1977

The feedback sources of oculomotor control system consist of three types of feedback path originating from retinal image displacement, in the proprioceptive fibers of the extraocular muscles, in the efference copy within the C.N.S. From above feedback loops, the retinal image feedback path is a main subject in this experiment. The electrical output of eye ball motion detecting with a photo-electric matrix method is fed into galvanometer through the external feedback path, and the stability was also examined.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.312-316
• /
• 2004

The paper presents a technique to identify the boundary of the optic disc in infant retinal digital images using an approach based on active contours (snakes). The technique can be used to be develop a automate system in order to help the ophthalmologist's diagnosis the retinopathy of prematurity (ROP) disease which may occurred on preterm infant,. The optic disc detection is one of the fundamental step which could help to create an automate diagnose system for the doctors we use a new kind of active contour (snake) method has been developed by Chenyang et. al. [1], based on a new type of external force field, called gradient vector flow, or GVF. GVF is computed as a diffusion of the gradient vectors of a gray-level or binary edge map derived from the image. The testing results on a set of infant retinal ROP images verify the effectiveness of the proposed methods. We show that GVF has a large capture range and it's able to move snakes into boundary concavities of optic disc and finally the optic disk boundary was determined.

• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1476-1485
• /
• 2020

Segmenting OCT retinal images into layers is important to diagnose and understand the progression of retinal diseases or identify potential symptoms. The task of manually identifying these layers is a difficult task that requires a lot of time and effort even for medical professionals, and therefore, various studies are being conducted to automate this using deep learning technologies. In this paper, we use cGAN-based neural network to automatically segmenting OCT retinal images into seven terrain-type regions defined by six layer boundaries. The network is composed of a Segnet-based generator model and a discriminator model. We also proposed a dynamic programming algorithm for refining the outputs of the network. We performed experiments using public OCT image data set and compared its performance with the Segnet-only version of the network. The experimental results show that the cGAN-based network outperforms Segnet-only version.

• Korean Journal of Optics and Photonics
• /
• v.19 no.6
• /
• pp.439-447
• /
• 2008

There is a need for a finite schematic presbyopic eye that models vision and image quality under various conditions such as cataract or refractive surgery, as well as near vision corrections with an ophthalmic lens or contact lens. Using recently measured biometric data of presbyopic eyes, new model eyes were designed that are optically and anatomically close to real eyes. The parameters changing significantly with age were incorporated into models for four different age groups. The new model eyes have alpha angle, decentered pupil, aspheric GRIN lens and aspheric retinal surface. It is likely that the new finite presbyopic model eyes will be useful for designing visual instruments such as low vision aids, PALs, IOL and contact lenses, and for the clinical prediction of the retinal image quality of a presbyopic patient.

• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.335-345
• /
• 2018

Objectives: The retinal nerve fiber layer (RNFL) is a site of glaucomatous optic neuropathy whose early changes need to be detected because glaucoma is one of the most common causes of blindness. This paper proposes an automated RNFL detection method based on the texture feature by forming a co-occurrence matrix and a backpropagation neural network as the classifier. Methods: We propose two texture features, namely, correlation and autocorrelation based on a co-occurrence matrix. Those features are selected by using a correlation feature selection method. Then the backpropagation neural network is applied as the classifier to implement RNFL detection in a retinal fundus image. Results: We used 40 retinal fundus images as testing data and 160 sub-images (80 showing a normal RNFL and 80 showing RNFL loss) as training data to evaluate the performance of our proposed method. Overall, this work achieved an accuracy of 94.52%. Conclusions: Our results demonstrated that the proposed method achieved a high accuracy, which indicates good performance.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2004.08a
• /
• pp.442-445
• /
• 2004

We report principles and results of design large FOV retinal display systems by software WinDEMOS and software for computer testing display systems TEDiS. We discuss results design head mounted and head up display. As combiner we are used volume interference recorded or synthetic HOE, and as the sours of the image high resolution transmitting or reflective liquid crystal matrixes on silicon (LCOS) or CRT.