46 skills found · Page 1 of 2
sunnyshah2894 / DigitalHairRemovalThere has been numeruous advancements towards utilizing deep networks, ANNs, AI, etc in tasks like detecting the skin disease, type of tumour, etc. However, it becomes difficult for the networks to learn the features since, most of the skin images are occluded by hair. Thus, there is a need for pre-processing of the skin images to remove these obstructing hair. This sample project aims to remove the hair noise from the skin image with the help of Morphological filtering.
etotheipi / CUDA Image ProcessingDeveloping a complete set of GPU-accelerated image processing tools, including convolution and morphology
andreybicalho / ExtendedMorphologicalProfilesRemote sensed hyperspectral image classification with Spectral-Spatial information provided by the Extended Morphological Profiles
DanielRapp / MorphMorphological image processing
HimaRaniMathews / Vehicle Detection Classification And CountingProject on Vehicle Detection, Classification, and Counting. Done in python using OpenCV.
kishan-vk / Automatic Blood Type Detection Using Image ProcessingDetermining of blood types is very important during emergency situation before administering a blood transfusion.presently,these tests are performed manually by technicians, which can lead to human errors. A method is developed based on processing of images acquired during the slide test.The image processing techniques such as Pre-processing, Segmentation, Thresholding, Morphological operatios and support vector machines are used. The images of the slide test are obtained from pathological laboratory are processed and the occurrence of agglutination are evaluated. Thus the developed automated method determines the blood type using image processing techniques.The devoloped method is useful in emergency situation to determine the blood group without human errors.
JuliaImages / ImageMorphology.jlMorphological operations for image processing
zahrasalarian / Digital Image Processing For Medical ApplicationsThis repository contains projects related to various aspects of image processing, from basic operations to advanced techniques like active contours. Examples and case studies focus on applications in medical imaging.
kamalkishor / Wound Image Segmentation By Markov Random FieldEnhanced 18% efficiency of a research project on Wound Image Segmentation using Markov Random Field, Image Processing, Segmentation and Morphology.
sarthak25 / Brain Tumor SegmentationThis repo is of segmentation and morphological operations which are the basic concepts of image processing. Detection and extraction of tumor from MRI scan images of the brain is done using python
seung-lab / FastmorphMultilabel and Grey 3D morphological image processing functions. Dilate, Erode, Opening, Closing, Hole Filling.
OluwaseunOjeleye / Image Processing AppThis repository contains the implementation of an Object Detection and Classification & Line and Circle Detection Application
bhaveshjaggi / PestDetectionPEST DETECTION USING IMAGE PROCESSING e The principal idea which empowered us to work on the project PEST DETECTION USING IMAGE PROCESSING is to ensure improved and better farming techniques for farmers. Our Solution: The techniques of image analysis are extensively applied to agricultural science, and it provides maximum protection to crops and also much less use of pesticides which can ultimately lead to better crop management and production. The following softwares are required for the project: OpenCV with C++/Python : It is a library which is designed for computational efficiency with a strong focus on real time applications. Pest Detection System Following are the image processing steps which are used in the proposed system. >Color Image to Gray Image Conversion Therefore, images are converted into gray scale images so that they can be handled easily and require less storage. The following equation shows how images are converted into gray scale images. I(x,y)=0.2989*B +0.5870*G +0.1140*B > Image Filtering The PSNR value is calculated for both the average and median resulting images .The average filter provides better result as compared to the median filter. So this paper uses average filter for further processing. > Image Segmentation To detect the pests from the images, the image background is calculated using morphological operators which is most critical after this image is subtracted from the original image. So the resulting image will only have the objects with pixel values 1 and background pixel values 0. >Noise Removal Noise contains dew drops, dust and other visible parts of leaves. As only the object of interest was to be visible on the images,so the aim was to remove the noise to get better and effective results. The Erosion algorithm has been used to remove isolated noisy pixels and to smoothen object boundaries . After noise removal,the next goal was to enhance the detected pests after segmentation which was performed by using the dilation algorithm. >Feature Extraction Different properties of the images are calculated on the basis of those attributes using which image is classified. For image properties, gray level co-occurrence matrix and regional properties of the images are calculated. These properties are used to train the support vector machine to classify images. >Counting of the pests on the leaves is the main purpose, so that it can give an idea of how much pests are there on a leaf.It uses Moore neighborhood tracing algorithm and Jacob's stopping criterion Feasibility: The present framework of pest detection is quite tedious and laborious for the farmers as they have to carry out their acre-acres surveys themselves and it requires a lot of vigorous efforts to achieve the same.Image analysis provides a realistic opportunity for the automation of insect pest detection.Through this system, crop technicians can easily count the pests from the collected specimens, and right pests’ management can be applied to increase both the quantity and quality of production. Using the automated system, crop technicians can make the monitoring process easier. So in order to bring enhancements in the system,we came up with more productive and well organised system with our idea .Due to this automaton applied,lucrativeness increases and labour is reduced.
yavuzKomecoglu / Digital Image Processing18-31 Ağustos 2019 tarihlerinde Bilgisayar Mühendisleri Odası ve Kadıköy Belediyesi (İDEA Kadıköy) tarafından düzenlenecek olan Yapay Zekâ Yaz Atölyesi için görüntü işleme dersi kapsamında hazırlanmıştır.
adamshch / GraFT AnalysisThis repository contains code for morphology-free analysis of functional fluorescence microscopy. The focal algorithm, Graph-Filtered Time-trace (GraFT) Dictionary Learning, is published in Charles et al. 2022 in the IEEE Transactions of Image Processing.
hexiaomo624 / Detection Of Road Surface Crack Based On PYNQThis project aims at the problem of road surface image denoising and crack recognition by using embedded camera. Using Gaussian filter to blur the image, over the threshold zero processing and the morphology on and off operation are binarization and further denoising. And the crack contour is marked by FAST feature point recognition, which reach for different road crack damage can be identified. After the simulation, the algorithm is transplanted to the Python on Zynq (PYNQ) system to achieve the purpose of crack identification. There are two parts to the innovation: First, using a lower-cost embedded camera to capture photos, and second, using the characteristics of large difference in gray value between crack region and other regions, the crack profile is marked by the way of FAST feature point recognition and use PYNQ to process. It makes the identification system more integrated and portable, and can judge the crack more accurately and reduce the cost.
dani-amirtharaj / ImageSegmentation Clustering MorphologicalProcessingPrograms to detect clusters in data using GMM and compressed images (Color Quantization) using k-means clustering methods, detect bone fragments in an X-ray image using Segmentation and de-noise binary images using Morphological Image Processing.
IshanMohanty / Digital Image Processing Computer Vision ToolboxImplementation of Bilinear interpolation for resizing, Histogram equalization for contrast manipulation, Oil paint & Film effect emulation, Image denoising, Geometrical warping, Digital-Halftoning, Homographic Transformation and Image Stitching, Morphological Processing, Texture Analysis and image segmentation, Edge Detection, SIFT and SURF algorithm for feature extraction, object matching and bag-of-words representation.
Daymenion / Image Editor With Pythonimage and photo editor with many extra features in python
Chinmay2911 / Player DetectionPlayer detection and ball detection in Football videos There are multiple ways to detect players in any sports videos.Here I have used simple image processing techniques to detect players by only using opencv. It detects first the green ground and make everything other then green color into black.After converting into greyscale I have found contours on the ground.By using some parameters we will detect players. Here I have used the video of France VS Belgium match.So for further detection, I have used the color of their jersy to segment them.For france We will detect the blue jersy and then for belgium we will detect the red jersy. Algorithm: First we will read the video. Detect the Green ground. Use morphological operation for better detection. Find contours. Detect players. Segment them by France or Belgium. Detect the football. You can see the code in player_detection.py and the video used is cutvideo.mp4.
