JigsawNet: Shredded Image Reassembly Using Convolutional Neural Network and Loop-Based Composition

Le, Canyu; Li, Xin

doi:10.1109/tip.2019.2903298

Cited by 27 publications

(7 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future work, this limitation could be resolved by implementing an automated method for finding adjacent fragments. For example, Le et al 9 demonstrated that a convolutional neural network can be used for identifying pairs of adjacent jigsaw puzzle pieces and that these pairs can then be used to reconstruct the original image. Another limitation of our work is that our current validation data only consisted of cases with either two or four tissue fragments.…”

Section: Resultsmentioning

confidence: 99%

PythoStitcher: an iterative approach for stitching digitized tissue fragments into full resolution whole-mount reconstructions

Schouten

Litjens

2023

Medical Imaging 2023: Digital and Computational Pathology

View full text Add to dashboard Cite

In histopathology, whole-mount sections (WMS) can be utilized to capture entire cross-sections of excised tissue, thereby reducing the number of slides per case, preserving tissue context, and minimizing cutting artefacts. Additionally, the use of WMS allows for easier correlation of histology and pre-operative imaging. However, in digital pathology, WMS are not frequently acquired due to the limited availability of whole-slide scanners that can scan double-width glass slides. Moreover, whole-mounts may still be too large to fit on a single double-width glass slide, and archival material is typically stored as tissue fragments. In this work, we present PythoStitcher, an improved version of the AutoStitcher algorithm for automatically stitching multiple tissue fragments and constructing a full-resolution WMS. PythoStitcher is based on a genetic algorithm that iteratively optimizes the affine transformation matrix for each tissue fragment using the Euclidean distance between corner points of neighbouring fragments. We demonstrate the efficiency and generalisability of PythoStitcher in a pilot validation of ten prostatectomy cases with four fragments and two oesophagectomy cases with two fragments. On average, PythoStitcher obtained the final stitching result in 60 seconds (range 51-73) for the prostatectomy cases and 68 seconds (range 43-94) for the oesophagectomy cases. The stitching accuracy was objectively evaluated by computing the average Euclidean distance between all corner points from the edges of neighbouring fragments. For the reconstructed WMS at full resolution, the average residual registration error was 1.6 mm (range 0.5-3.2) for the prostatectomy cases and 2.1 mm (range 0.5-3.8) for the oesophagectomy cases. The key strengths of PythoStitcher include its computational efficiency, the ability to reconstruct the WMS in full resolution, and an open-source implementation in Python.

show abstract

Section: Resultsmentioning

confidence: 99%

PythoStitcher: an iterative approach for stitching digitized tissue fragments into full resolution whole-mount reconstructions

Schouten

Litjens

2023

Medical Imaging 2023: Digital and Computational Pathology

View full text Add to dashboard Cite

show abstract

“…This means that the relative positions of the pixels in space and its channel have changed, thereby destroying the visual features and information structure of the original image. JigsawNet employs DNNs to construct latent relationships between sub-images, thereby attempting to piece together the original image [30]. It represents another heuristic attack method.…”

Section: Heuristic Attacks By Shredder Challenge Algorithmmentioning

confidence: 99%

You Can Use But Cannot Recognize: Preserving Visual Privacy in Deep Neural Networks

Li,

Zhang,

Ren

et al. 2024

Proceedings 2024 Network and Distributed System Security Symposium

View full text Add to dashboard Cite

Image data have been extensively used in Deep Neural Network (DNN) tasks in various scenarios, e.g., autonomous driving and medical image analysis, which incurs significant privacy concerns. Existing privacy protection techniques are unable to efficiently protect such data. For example, Differential Privacy (DP) that is an emerging technique protects data with strong privacy guarantee cannot effectively protect visual features of exposed image dataset. In this paper, we propose a novel privacy-preserving framework VisualMixer that protects the training data of visual DNN tasks by pixel shuffling, while not injecting any noises. VisualMixer utilizes a new privacy metric called Visual Feature Entropy (VFE) to effectively quantify the visual features of an image from both biological and machine vision aspects. In VisualMixer, we devise a task-agnostic image obfuscation method to protect the visual privacy of data for DNN training and inference. For each image, it determines regions for pixel shuffling in the image and the sizes of these regions according to the desired VFE. It shuffles pixels both in the spatial domain and in the chromatic channel space in the regions without injecting noises so that it can prevent visual features from being discerned and recognized, while incurring negligible accuracy loss. Extensive experiments on real-world datasets demonstrate that VisualMixer can effectively preserve the visual privacy with negligible accuracy loss, i.e., at average 2.35 percentage points of model accuracy loss, and almost no performance degradation on model training.

show abstract

“…Closing loop detection has a new approach thanks to the rapid development of deep learning techniques [29,30,31,32,33,34]. VSLAM closed-loop detection [35] is fundamentally a scene recognition problem, and deep learnbased detection and recognition methods have attracted widespread attention.…”

Section: Related Workmentioning

confidence: 99%

CAE-VLAD-Net: A Loop Closure Detection System for Mobile Robots Using Convolutional Auto-Encoders Network with VLAD

Zhang

et al. 2023

Preprint

View full text Add to dashboard Cite

A critical part of visual SLAM is visual loop closure detection. It can solve the problem of trajectory drift caused by long time movement of mobile robots. The traditional loop closure detection system can not accurately detect the real closed loop. Factors such as different viewpoints, different lighting conditions and dynamic feature occlusion can seriously affect the positioning accuracy of mobile robots. Deep learning is made significant strides in computer visual in recent years, offering a fresh approach to the closing loop detection challenge. In this paper, We build a loop closure algorithm based on CAE-VLAD-Net (Convolutional Auto-Encoder-Vector of Locally Aggregated Descriptors-Network) model, which can solve these problems. This algorithm combines the characteristics of convolutional neural networks and stacked auto-encoders in deep learning, extracts features of continuous dense data collected by sensors, and applies them in loop closure based on key frames. We conduct comprehensive tests on various datasets, demonstrating that our method performs better than the state-of-the-art approach.

show abstract

JigsawNet: Shredded Image Reassembly Using Convolutional Neural Network and Loop-Based Composition

Cited by 27 publications

References 38 publications

PythoStitcher: an iterative approach for stitching digitized tissue fragments into full resolution whole-mount reconstructions

PythoStitcher: an iterative approach for stitching digitized tissue fragments into full resolution whole-mount reconstructions

You Can Use But Cannot Recognize: Preserving Visual Privacy in Deep Neural Networks

CAE-VLAD-Net: A Loop Closure Detection System for Mobile Robots Using Convolutional Auto-Encoders Network with VLAD

Contact Info

Product

Resources

About