HED-CoreML
Image detection framework
A framework for applying Holistically-Nested Edge Detection to image processing using CoreML and Swift.
Holistically-Nested Edge Detection (HED) using CoreML and Swift
108 stars
7 watching
22 forks
Language: Swift
last commit: over 7 years ago
Linked from 1 awesome list
caffecoremlhedswift
Related projects:
Repository | Description | Stars |
---|---|---|
| An edge detection algorithm that uses deep learning to predict images from hierarchical representations | 1,808 |
| Automatically detects and crops faces, texts, or barcodes from images using the iOS 11 Vision API | 307 |
| An unsupervised object detection and segmentation framework that can learn from image data alone, without requiring human annotations. | 954 |
| An open-source implementation of the SegNet deep learning architecture for image segmentation | 1,080 |
| A deep learning-based object detection system from scratch | 706 |
| A software framework implementing an alignment-free RGBT salient object detection algorithm using a semantics-guided asymmetric correlation network | 10 |
| A Swift wrapper around the libgd graphics library to provide basic image manipulation functionality on server-side Swift applications. | 458 |
| A demo project demonstrating the integration of Core ML and Vision Framework with Swift 4 for image classification using an Inception V3 network. | 217 |
| An implementation of a unified framework for object detection using a single network. | 109 |
| A standalone Ada package for decoding various image formats from different data streams. | 25 |
| A deep learning model that uses 3D point cloud data to improve the precision of single-stage object detection in autonomous vehicles. | 492 |
| An optimized deep learning framework for action recognition tasks | 26 |
| A simple cross-platform HUD (Heads-Up Display) solution written in Swift for iOS applications. | 139 |
| A deep neural network architecture for segmenting images into distinct regions of interest | 205 |
| This project presents a framework for federated domain generalization in medical image segmentation using continuous frequency space and episodic learning. | 246 |