blog

Animal Monitoring With Pattern Recognition

Automatic Identification of Pigs in a Pen Using Pattern Recognition The growing demand for animal products is characterized, at the farmer’s end, by an

On-Combine, Multi-Sensor Environmental Data Collection

Article Summary: On-Combine, Multi-Sensor Data Collection for Post-harvest Assessment of Environmental Stress in Wheat Continuing our series examining interesting articles in the field of computer

Applications in Precision Agriculture

Image Processing Applications in Precision Agriculture In this page, you will learn about image processing applications for precise agriculture. If you want to boost your

Indoor Scene Structure Analysis

Summary: Indoor Scene Structure Analysis for Single Image Depth Estimation This is the first of our series of summaries of interesting texts on computer

Automatic Catheter Orientation Measurement

Catheters are inserted with measurement equipment at their tips, in order to scan their immediate surroundings. While orientation of the catheter’s tip is unknown throughout insertion, RSIP Vision has employed advanced algorithmic techniques to provide an exact measurement of catheter orientation during angiography, enabling the physician to ascertain the orientation of the catheter’s tip from x-ray images.

Quantitative Coronary Analysis

The main contribution of Quantitative Coronary Analysis (QCA) consists in measuring the diameter of arteries. Angiograms provide coronary images of region suspected of lesions using which our advanced algorithms for vessel detection and segmentation measure the segmented artery’s diameter. Abnormal values (as compared to a constructed reference diameter) are suspected as stenosis. Our system extracts and displays relevant values to the view of medical professionals and their patients.

Right Atrium Measurement with Ultrasound

Right Atrium Measurement in Ultrasound Videos Atrial fibrillation is an irregular rhythmic beating of the heart associated with coronary heart disease, high blood pressure

Finding Cysts, Part Five: Final Detection

The goal is to automatically detect the appearance of Cystoid Macular Edema (CME) in Optical Coherence Tomography (OCT) images. The deep learning technique used, Convolutional Neural Networks, takes as an input patches of pixels from within the retina. These patches were generated from previous segmentation of retinal images. A further segmentation of the retina is performed using an image processing algorithm called SLIC. Every superpixel thus generated, after being labeled as in the OCT scan, is fed into the neural network to detect the cyst.

Explaining OCT Scans

What are OCT Scans? Optical coherence tomography (OCT) is a non-invasive imaging method, which produces high-resolution volumetric histological images of tissue. To penetrate deep into biological

Finding Cysts Part Four: Seed Detection

A series of five articles on our Cysts Detection project using deep learning and Convolutional Neural Networks: 1) our cyst detection method; 2) the cyst denoising process; 3) the retinal layer segmentation; 4) the automatical seed-detection; 5) the final detection of the cysts. Our method is exceptionally successful at finding the cysts themselves and most of their area. Remarkable results are achieved even when using relatively small datasets in the training process.