Shanq-Jang Ruan

Title: Shanq-Jang Ruan: Inventor in Image Recognition and Object Detection.

Introduction

Shanq-Jang Ruan is an inventor based in Taipei, Taiwan, whose patent work focuses on image recognition and object detection using convolutional neural networks. He is associated with the Industrial Technology Research Institute. His portfolio includes 2 patents.

Latest Patents

Ruan’s listed patents address methods for recognizing images and detecting objects with neural-network-based systems.

- **Image recognition method for detection tasks based on single convolutional neural network and image recognition system thereof.** This invention uses a single convolutional neural network to produce shared features for multiple detection tasks. An end-layer network module uses those features to generate separate recognition results, which the system then outputs.

- **Object detection method using CNN model and object detection apparatus using the same.** This invention processes sensor data through an initial object-detection algorithm, followed by stages of sparse update mapping and spatial pooling. Deep convolution layers extract features, and the system uses the final-stage feature result to make a detection prediction.

Career Highlights

Ruan’s patent work reflects an interest in applying convolutional neural networks to practical recognition and detection tasks. His inventions describe approaches for sharing features across multiple image-recognition tasks and refining object-detection results through staged processing.

Collaborations

Ruan’s listed coworkers include Peter Chondro and Wei-Hao Lai. His work is associated with the Industrial Technology Research Institute.

Conclusion

Shanq-Jang Ruan’s patents focus on neural-network methods for image recognition and object detection, including shared-feature processing and staged refinement of detection results.