22 skills found
transybao1393 / Face Recognition PipelineFace recognition pipeline based on Facenet and MTCNN including image preprocessing (denoise, dehazing,...) with image augmentation techniques
HistoCleanQUB / HistoCleanHistoClean is a tool for the preprocessing and augmentation of images used in deep learning models. This easy to use application brings together the most popular image processing packages from across the python universe, meaning no more looking at documentation! HistoClean provides real time feedback to augmentations and preprocessing options. This allows users to evaluate their steps before implementation.
aimclub / ODRSRecomendation System
Badshah-CoderZ / Deepvision Dataset ToolkitImage dataset preprocessing CLI — labeling, resizing, augmentation
james77777778 / Keras AugA library that includes Keras 3 preprocessing and augmentation layers, providing support for various data types such as images, labels, bounding boxes, segmentation masks, and more.
kbhujbal / Autopilot CNN Self Driving Car Simulation With Behavioral Clonning🌐🚘 End-to-end Autonomous Driving implemented via Behavioral Cloning (BC) on the Udacity SDC platform. The core is a highly robust NVIDIA CNN architecture leveraging Deep Learning to map raw pixels directly to steering commands. It features advanced Image Augmentation for superior generalization on complex, unseen tracks.
chehao2628 / CNN SystemKeywords: CNN, Fully connect neural network, SFEW dataset, Image Preprocessing, Data Augmentation, Leakey ReLU, k-fold cross validation, Casper. In this project, I build my own CNN system with Image Preprocessing and Data Augmentation which are based on the computation ability and characteristic of used Dataset. This project implemented with Pytorch.
deadskull7 / Cats Vs Dogs CNN Using Keras The training set consisted of 25,000 images out of which 5,000 images were taken out as validation data. Separate test data folder consisted of 12,500 images for which the labels were predicted using trained model. My work includes preprocessing for model, Data augmentation to prevent overfitting, callbacks in keras to reduce learning rate timely, various CNN architecture trials with different layers and hyperparameters for best fit and learning curve wrt epochs. I gained a validation accuracy of 87.15 % without using any pretrained imagenet models . VGG-16 gave around 89 % as validation accuracy.
ParulParima / LabelMe Image Data Augment This script is used to augment image data created using LabelMe-MIT.
thisishardik / Electrical Substation DetectionMachine Learning based feature extraction of electrical substations from satellite data. Powered by IEEE-ICETCI, RRSC-Central, NRSC, and ISRO, this project incorporates instance segmentation of substations using UNet, Albumentations for image augmentation, and OpenCV for computer vision tasks.
PeterAugustin243 / CNN Based Image ClassifierA deep learning-based image classifier built with MobileNetV2 to recognize shoes, clips, and toothbrushes. The project includes preprocessing, normalization, and advanced data augmentation for robust training. It features fine-tuned transfer learning and a prediction pipeline with confidence scoring.
dpavansekhar / Food Freshness Detection Using Deep LearningThis project classifies fruit quality into five levels (Fresh to Rotten) using image preprocessing, data augmentation, and clustering (K-Means, Agglomerative, DBSCAN). Deep learning models are trained on clustered data, with AlexNet + Agglomerative Clustering achieving top results (Acc: 0.84, F1: 0.83).
Tirth8038 / Multiclass Image Classification The main aim of the project is to scan the X-rays of human lungs and classify them into 3 given categories like healthy patients, patients with pre-existing conditions, and serious patients who need immediate attention using Convolutional Neural Network. The provided dataset of Grayscale Human Lungs X-ray is in the form of a numpy array and has dimensions of (13260, 64, 64, 1). Similarly, the corresponding labels of X-ray images are of size (13260, 2) with classes (0) if the patient is healthy, (1) if patient has pre-existing conditions or (2) if patient has Effusion/Mass in the lungs. During data exploration, I found that the class labels are highly imbalanced. Thus, for handling such imbalanced class labels, I used Data augmentation techniques such as horizontal & vertical flips, rotation, altering brightness and height & width shift to increase the number of training images to prevent overfitting problem. After preprocessing the data, the dimension of the dataset is (31574, 64, 64, 1). For Model Selection, I built 4 architectures of CNN Model similar to the architecture of LeNet-5, VGGNet, AlexNet with various Conv2D layers followed by MaxPooling2D layers and fitted them with different epochs, batch size and different optimizer learning rate. Moreover, I also built a custom architecture with comparatively less complex structure than previous models. Further to avoid Overfitting, I also tried regularizing Kernel layer and Dense layer using Absolute Weight Regularizer(L1) and to restrict the bias in classification, I used Bias Regularizer in the Dense layer. In addition to this, I also tried applying Dropout with a 20% dropout rate during training and Early Stopping method for preventing overfitting and evaluated that Early Stopping gave better results than Dropout. For evaluation of models, I split the dataset into training,testing and validation split with (60,20,20) ratio and calculated Macro F1 Score , AUC Score on test data and using the Confusion Matrix, I calculated the accuracy by dividing the sum of diagonal elements by sum of all elements. In addition to this, I plotted training vs. validation loss and accuracy graphs to visualize the performance of models. Interestingly, the CNN model similar to VGGNet with 5 Conv2D and 3 MaxPooling layers and 2 Dense layers performed better than other architecture with Macro F1 score of 0.773 , AUC score of 0.911 and accuracy of 0.777.
manishkumar03 / SwiftPixelUtilsHigh-performance Swift library for ML image preprocessing & postprocessing. One-line APIs for TFLite, CoreML, PyTorch/ExecuTorch. Supports classification, detection (YOLO), segmentation (DeepLabV3), quantization, augmentation, and visualization.
Miao025 / Computer Vision MIAS 3classification3-class MIAS breast cancer classification system using early fusion of features from fine-tuned VGG16, VGG19, ResNet50, and DenseNet121. Multiple image preprocessing, data augmentation, upsampling, and adjusted weighted loss for better model performance.
M-Husnain-Ali / White Blood Cell ClassificationWhite Blood Cell Classification is a deep learning project built with Python, TensorFlow, and Keras that classifies five types of WBCs from microscopic images using a CNN model. With advanced image preprocessing, data augmentation, and a robust architecture, it achieves up to 95% test accuracy.
OmarSamirz / Fine Tuning An Arabic OCR Model Using Tesseract 5.0This research aims to fine-tune an Arabic OCR model using Tesseract 5.0, enhancing text recognition accuracy through extensive data collection, preprocessing, and image generation. By leveraging advanced training techniques and data augmentation, we achieve significant improvements in word error rates (WER).
Abhradipta / Facial Expression RecognitionFacial Expression Classification Using Convolutional Neural Network And Residual Neural Networks.
imdeepmind / HocroxHocrox: An image preprocessing and augmentation library with Keras like interface.
TawfiqMohammed / 3D Brain Tumor DetectionThis project uses a 3D U-Net model to perform brain tumor segmentation on MRI scans, identifying tumor regions with high accuracy. Includes data preprocessing, 3D data augmentation, and visualization tools for analyzing segmentation outputs. Ideal for applications in medical imaging research and clinical support.
