About

Edward K. Wong is an Associate Professor in the Department of Computer Science and Engineering at NYU Tandon School of Engineering. He received his Bachelor of Engineering degree from the State University of New York at Stony Brook in 1979, his Sc.M. degree from Brown University in 1981, and his Ph.D. in Electrical Engineering from Purdue University in 1986. His research interests encompass image processing, computer vision, and pattern recognition. Dr. Wong has published extensively in these areas and has secured research funding from federal and state government agencies as well as private industry. He has served as a technical consultant to several companies in the New York area and is currently an associate editor for the Springer LNCS Transactions on Data Hiding and Multimedia Security. Additionally, he has participated in organizing and technical program committees for major conferences, contributing to the advancement of his field.

Research topics

• Artificial Intelligence
• Computer Science
• Computer vision
• Geology
• Remote sensing
• Algorithm

Selected publications

• Confidence Trigger Detection: Accelerating Real-Time Tracking-by-Detection Systems

  2024-05-31 · 7 citations

  articleSenior author

  Real-time object tracking necessitates a delicate balance between speed and accuracy, a challenge exacerbated by the computational demands of deep learning methods. In this paper, we introduce Confidence-Triggered Detection (CTD), a novel approach that strategically skips object detection for frames exhibiting high similarity, leveraging tracker confidence scores. CTD not only enhances tracking speed but also preserves accuracy, surpassing existing tracking algorithms. Through extensive evaluation across various tracker confidence thresholds, we identify an optimal trade-off between tracking speed and accuracy, providing crucial insights for parameter fine-tuning and enhancing CTD's practicality in real-world scenarios. Furthermore, our experiments across diverse detection models underscore the robustness and versatility of the CTD framework, demonstrating its potential to enable real-time tracking in resource-constrained environments.

  PublisherDOI

• URCA-GAN: UpSample Residual Channel-wise Attention Generative Adversarial Network for image-to-image translation

  Neurocomputing · 2021 · 25 citations

  Senior authorCorresponding
  • Computer Science
  • Artificial Intelligence
  • Computer Science
  PublisherDOI

• GiGAN: Gate in GAN, could gate mechanism filter the features in image-to-image translation?

  Neurocomputing · 2021-08-02 · 4 citations

  articleSenior author
  PublisherDOI

• Attention Mask R-CNN for Ship Detection and Segmentation From Remote Sensing Images

  IEEE Access · 2020 · 194 citations

  Senior authorCorresponding
  • Computer Science
  • Artificial Intelligence
  • Computer Science

  In recent years, ship detection in satellite remote sensing images has become an important research topic. Most existing methods detect ships by using a rectangular bounding box but do not perform segmentation down to the pixel level. This paper proposes a ship detection and segmentation method based on an improved Mask R-CNN model. Our proposed method can accurately detect and segment ships at the pixel level. By adding a bottom-up structure to the FPN structure of Mask R-CNN, the path between the lower layers and the topmost layer is shortened, allowing the lower layer features to be more effectively utilized at the top layer. In the bottom-up structure, we use channel-wise attention to assign weights in each channel and use the spatial attention mechanism to assign a corresponding weight at each pixel in the feature maps. This allows the feature maps to respond better to the target’s features. Using our method, the detection and segmentation mAPs increased from 70.6% and 62.0% to 76.1% and 65.8%, respectively.

  PublisherOA PDFDOI

• Syntactic Image Pattern Recognition

  2020-08-11

  book-chapter1st authorCorresponding

  This chapter describes string grammers for pattern description/analysis. It describes syntactic pattern recognition procedures, including parsing, error-correcting parsing, and sentence-to-sentence clustering techniques. The chapter describes two-dimensional grammars for image patterns. In machine recognition of image patterns and shapes, features are extracted and subject to statistical analysis; or primitives are selected and subject to syntax analysis. The former is called the statistical or decision-theoretic approach, and the latter is called the syntactic or structural approach, The statistical or decision-theoretic approach is the traditional approach to pattern recognition that has been studied since the 1960s. Depending on the image pattern, different segmentation or decomposition processes can be applied. Once the primitives are extracted, they are represented symbolically using a string or a sentence, or other pattern representation languages.

  PublisherDOI

• Confidence Trigger Detection: An Approach to Build Real-time Tracking-by-detection System

  arXiv (Cornell University) · 2019-02-02 · 1 citations

  preprintOpen accessSenior author

  With deep learning based image analysis getting popular in recent years, a lot of multiple objects tracking applications are in demand. Some of these applications (e.g., surveillance camera, intelligent robotics, and autonomous driving) require the system runs in real-time. Though recent proposed methods reach fairly high accuracy, the speed is still slower than real-time application requirement. In order to increase tracking-by-detection system's speed for real-time tracking, we proposed confidence trigger detection (CTD) approach which uses confidence of tracker to decide when to trigger object detection. Using this approach, system can safely skip detection of images frames that objects barely move. We had studied the influence of different confidences in three popular detectors separately. Though we found trade-off between speed and accuracy, our approach reaches higher accuracy at given speed.

  Publisher

• Cross-Safe: A Computer Vision-Based Approach to Make All Intersection-Related Pedestrian Signals Accessible for the Visually Impaired

  Advances in intelligent systems and computing · 2019-04-23 · 36 citations

  book-chapter
  PublisherDOI

• Deep Learning with Feature Reuse for JPEG Image Steganalysis

  2018-11-01 · 5 citations

  article

  It is challenging to detect weak hidden information in a JPEG compressed image. In this paper, we propose a 32-layer convolutional neural networks (CNNs) with feature reuse by concatenating all features from previous layers. The proposed method can improve the flow of gradient and information, and the shared features and bottleneck layers in the proposed CNN model further reduce the number of parameters dramatically. The experimental results shown that the proposed method significantly reduce the detection error rate compared with the existing JPEG steganalysis methods, e.g. state-of-the-art XuNet method and the conventional SCA-GFR method. Compared with XuNet method and conventional method SCA-GFR in detecting J-UNIWARD at 0.1 bpnzAC (bit per non-zero AC DCT coefficient), the proposed method can reduce detection error rate by 4.33% and 6.55% respectively.

  PublisherDOI

• Spatial Image Steganography Based on Generative Adversarial Network

  arXiv (Cornell University) · 2018-04-21 · 67 citations

  preprintOpen access

  With the recent development of deep learning on steganalysis, embedding secret information into digital images faces great challenges. In this paper, a secure steganography algorithm by using adversarial training is proposed. The architecture contain three component modules: a generator, an embedding simulator and a discriminator. A generator based on U-NET to translate a cover image into an embedding change probability is proposed. To fit the optimal embedding simulator and propagate the gradient, a function called Tanh-simulator is proposed. As for the discriminator, the selection-channel awareness (SCA) is incorporated to resist the SCA based steganalytic methods. Experimental results have shown that the proposed framework can increase the security performance dramatically over the recently reported method ASDL-GAN, while the training time is only 30% of that used by ASDL-GAN. Furthermore, it also performs better than the hand-crafted steganographic algorithm S-UNIWARD.

  PublisherOA PDFDOI

• JPEG steganalysis with combined dense connected CNNs and SCA-GFR

  Multimedia Tools and Applications · 2018-12-13 · 17 citations

  article
  PublisherDOI

Frequent coauthors

• Nasir Memon

  New York University

  11 shared

• Alexander Stibor

  8 shared

• Yao Wang

  New York University

  8 shared

• Minya Chen

  Wuxi People's Hospital

  7 shared

• Jenghwa Chang

  7 shared

• Yi Fang

  Shanghai Jiao Tong University

  7 shared

• Xuan Zhao

  7 shared

• John‐Ross Rizzo

  6 shared