Blog Archives - RSIP Vision

Cardiac Left Ventricle Segmentation

Cardiac MRI is used to assess the status of patients suffering from heart diseases like cardiac masses and thrombi, aortic and/or different kinds of congenital cardiac diseases. Cardiac MRI is minimally invasive, does not involve radiation and it generally delivers excellent images for diagnostics. However, automatic segmentation of the left ventricle on MRI images faces challenging difficulties, like locating the left ventricle and overcoming the lack of edge information. We propose a method providing a very robust input for daily clinical application.

Lesion Border Detection

Dermascopy is one of the main modalities used to detect skin abnormalities and lesions such as malignant melanoma. It is estimated that in the United

Left Ventricle Statistical Shape Modelling

Statistical shape modelling is a powerful tool for visualizing geometric and functional patterns of variation in all organs and also a reliable left ventricle shape model can prove itself very useful, though quite challenging to construct. RSIP Vision knows how to do this and many other image processing solutions for cardiology. And since cardiovascular diseases account for million of deaths per year in the developed world, this work is of vital importance.

Fabric Inspection with Texture Analysis

Vision-based production inspection systems using camera-based scanning are now quite common in in-line production lines such as in steel, leather and fabrics manufacturing. Inspection is a crucial process since it can reduce process and enhance product quality. We recommend here a texture analysis for defect and novelty detection in fabrics and non-structured surfaces. Our fabric inspection algorithms are developed to detect deviations from local pattern and texture, anomalies and defects.

3D inspection and crack detection

Industrial production is prone to surface defects and it often needs to be inspected prior to shipment, when still in a semi-finished status. Cracks being very frequent in many types of material, vision-based crack inspection and detection is cost effective and offers high reproducibility and reliability. Here is a contact-free procedure using laser scanning, which can be placed in-line for continuous inspection during production.

Road signs detection with machine learning

Frequent variations of speed limits (mainly due to roadwork and other maintenance), offer ADAS technology a chance to help drivers respect traffic laws and security. The traffic signs detection software developed by RSIP Vision detects a road sign at distance and verifies via machine learning if it is a speed limit sign and what that limit is. These detection and classification processes being based on machine learning, our application is able to do things that regular “engineered” software cannot do.

Flat Panel Display Inspection

This project compares the performance of a new inspection procedure of Flat Panel Displays (FPD) with the results obtained using a previously existing process. The goal was to demonstrate the correct detection and defect position reported by the new technology. This was done by putting in place a system in charge of image acquisition software and control which drives the captured frames to a sophisticated algorithmical registration analysis system developed by RSIP Vision.

Computer chipset track - with visible defects

Wafer defect detection by feature matching

Detection of microscopic defect in wafers and printed circuit boards is a standard procedure in the manufacturing process. The time consuming human inspection has been replaced in nearly all production lines with an automatic in-line camera-based examination, which can be very effective usingcomputer vision and image processing technologies to detect any anomalies. Via algorithms of feature extraction and matching, RSIP Vision is able to track defects leading to dramatically improvements in reliability and usability.

Detect barcode or QR with camera-based scanners

Barcode Detection in complex environments

Automatically localizing and reading barcodes captured by a smartphone-based cameras have great value for industrial and personal applications but create new technical challenges: quality of the image, motion blurs, unpredictable distance to barcode, non-uniform orientation and unknown location of the barcode itself. Image processing and computer vision algorithms can solve these issues: ask RSIP Vision how we do it.

Real time OCR in natural scenes

With the advancement in technology, the demand for OCR in natural environment is growing, even though outdoor conditions are far from being optimal for machine vision applications: occlusion of written text, text orientation, font style, blurring due to camera motion, and lighting conditions can prove themselves significant challenges in the task of performing real time OCR. Great progress has recently been made in the recognition of characters partially occluded and under heavy noise. RSIP Vision tells you how.

Microscopy imaging of metastatic cancer cells

Trajectory tracking of a fluorescent tag

Studying the behavior of bio-molecules and the interaction they have with other molecular structures in their native environment, developing indirect measuring procedures based on tracking of single particle, provides valuable information about processes like viral infections of cells, protein-DNA interactions and other complex biological processes. Analysis of trajectories of a tagged particle is one of many RSIP Vision’s projects tracking objects in a sequence of images with dynamic programming, one of our fields of expertise.

Silicon nanowires observed with an electron microscope

Reconstruction of rough surfaces with shape from focus

Reconstruction of the 3D shape of a surface viewed under the microscope is particularly challenging, owing to the irregular shapes that a surface can take. Irregular surfaces having many sharp bends and peaks have a high frequency texture pattern which needs to be smoothed out through a low-pass filter. The shape-from-focus method provides the framework to do just that, thanks to its ability to stably reconstruct a high frequency surface, as seen in electron microscopy.

Detecting Mitosis Using Deep Neural Networks

State and progression of breast cancer are assessed through prognostic factors, one of which is the mitotic figure. In a histological sample taken from patients, the fraction of breast tissue cells undergoing replication is used to grade the cancer. RSIP Vision’s algorithms allow fast detection, recognition and classification of the mitotic state of a cell using automatic computational autonomous tools: deep neural networks help distinguish complex patterns in images and finally differentiate between mitotic and non-mitotic cells.

Automatic segmentation of tumor cells

Molecular analysis of in histology enables quantification of abnormality in a given tissue, assess patient condition, and devise treatment. Tissue samples taken in biopsy allow researchers to screen for therapeutic agents but might not accurately capture the bulk tumor, due to its irregular non-cylindrical shape. This calls for an automated segmentation of tumor cells: RSIP Vision does that in several phases, concluded by machine learning methods which study the cell texture and classify the image accordingly. The end result is a fast and life-saving biopsy scanning and analysis system.

Bones and Skeleton segmentation

RSIP Vision suggests an automatic segmentation procedure based on iterative binarization of bone tissues density, as observed in Computed Tomography (CT), the most common 3D process used for bone imaging. This method is particularly fast, regardless of whether contrast was used in the CT scans. In fact, images taken with contrast generally display blood with an intensity which is similar to bone; our technique is able to overcome this challenge and to deliver a fast and satisfying bones segmentation and skeleton segmentation solution to our client.

Lungs tumors and nodules segmentation with Deep Learning

It is visually more difficult to identify lung tumors than nodules, since the latter are supposed to have an elliptical shape, while the chromatic aspect of the former is quite hard to distinguish from healthy tissues on a CT image. We use Deep Learning neural networks to overcome this difficulty in a way that is quick to perform, reliable and memory efficient. Our software of computer vision in pulmonology detects and classifies tumors and nodules in the fastest time, to provide our clients a quick and reliable 3D segmentation of lung tumors with Deep Learning.

Brain tumor segmentation

In addition to primary tumors, the human brain can also suffer from secondary tumors or brain metastases. The most common cancers that spread from remote areas to the brain are lung, breast, melanoma, kidney, nasal cavity and colon cancers. By the way of segmenting the tumor in the image, brain tumor image processing overcomes anatomical structure challenges. AI-based techniques enable to estimate the volume and spread of the tumor and provide objective and variation-free expected tumor boundaries.

Prostate segmentation in MR images

Prostate cancer is the second most common cancer among American men, with more than 200,000 new cases diagnosed every year and about 1 man in 7 diagnosed during his lifetime. Volume is a key indicator of the health of the prostate, revealing key information about the stage of the cancer, the probable prognosis and viable treatment. The rich experience of RSIP Vision enables us to recommend an approach based on a semi-automatic prostate segmentation to give a precise estimate of the prostate volume.

Lung Nodule Classification

Lung cancer early detection is a vital task which is made difficult by the small size of pulmonary nodules, the detection of which on thousands of CT scans every day is excessively time-consuming. Computer-aided lung nodule classification can dramatically boost the speed of diagnosis. Recommended solution starts from bidimensional images obtained from CT scan and displaying suspicious nodules areas: these are inserted into an autoencoder, from which two hundred dimensional features are extracted. These learned features are then confronted with a trained classifier to produce the final lung nodules classification.

Chest CT Registration

Lung cancer is the leading cancer killer of men and women in the U.S. and it causes more deaths than colorectal, breast and prostate cancers

Get in touch

Please fill the following form and our experts will be happy to reply to you soon