Machine‐Learning‐Based Image Similarity Analysis for Use in Materials Characterization

2020 ◽  
Vol 3 (3) ◽  
pp. 1900237 ◽  
Author(s):  
Zhi‐Lei Wang ◽  
Toshio Ogawa ◽  
Yoshitaka Adachi
Keyword(s):  
Machine Learning ◽  
Materials Characterization ◽  
Image Similarity ◽  
Similarity Analysis

Enhanced image similarity analysis system in digital pathology

2017 ◽  
Vol 76 (23) ◽  
pp. 25477-25494
Author(s):  
Jae-Gu Lee ◽  
Kyung-Chan Choi ◽  
Seung-Ho Yeon ◽  
Jeong Won Kim ◽  
Young-Woong Ko
Keyword(s):  
Digital Pathology ◽  
Image Similarity ◽  
Similarity Analysis ◽  
Analysis System

Image similarity analysis on MIE encryption algorithm

2010 ◽  
Author(s):  
Xiaoqiang Zhang ◽  
Shilong Ma ◽  
Guiliang Zhu ◽  
Weiping Wang ◽  
Mengmeng Wang
Keyword(s):  
Image Similarity ◽  
Encryption Algorithm ◽  
Similarity Analysis

scholarly journals Computational timbre and tonal system similarity analysis of the music of Northern Myanmar-based Kachin compared to Xinjiang-based Uyghur ethnic groups

2021 ◽  
Author(s):  
Rolf Bader ◽  
Michael Blaß ◽  
Jonas Franke
Keyword(s):  
Machine Learning ◽  
Feature Extraction ◽  
Standard Deviation ◽  
Ethnic Groups ◽  
Western China ◽  
Similarity Analysis ◽  
Self Organizing Map ◽  
Musical Piece ◽  
Sound Recordings ◽  
Spectral Centroid

The music of Northern Myanmar Kachin ethnic group is compared to the music of western China, Xijiang based Uyghur music, using timbre and pitch feature extraction and machine learning. Although separated by Tibet, the muqam tradition of Xinjiang might be found in Kachin music due to myths of Kachin origin, as well as linguistic similarities, e.g., the Kachin term 'makan' for a musical piece. Extractions were performed using the apollon and COMSAR (Computational Music and Sound Archiving) frameworks, on which the Ethnographic Sound Recordings Archive (ESRA) is based, using ethnographic recordings from ESRA next to additional pieces. In terms of pitch, tonal systems were compared using Kohonen self-organizing map (SOM), which clearly clusters Kachin and Uyghur musical pieces. This is mainly caused by the Xinjiang muqam music showing just fifth and fourth, while Kachin pieces tend to have a higher fifth and fourth, next to other dissimilarities. Also, the timbre features of spectral centroid and spectral sharpness standard deviation clearly tells Uyghur from Kachin pieces, where Uyghur music shows much larger deviations. Although more features will be compared in the future, like rhythm or melody, these already strong findings might introduce an alternative comparison methodology of ethnic groups beyond traditional linguistic definitions.

The Image Similarity Analysis Technique Applied to the Tool Wear Monitoring in Face Milling

2006 ◽  
Vol 315-316 ◽  
pp. 628-631
Author(s):  
Yu Teng Liang ◽  
C.J. Lo ◽  
W.C. Chen
Keyword(s):  
Tool Wear ◽  
Vision System ◽  
Image Data ◽  
Face Milling ◽  
Image Similarity ◽  
Similarity Analysis ◽  
Analysis Technique ◽  
Milling Operation ◽  
The Face ◽  
Wear Monitoring

The purpose of this paper is to monitor the tool wear based on the image data of cutting tool in the face milling operation. The surface images of the different coated inserted blade cutters are captured using a machine vision system incorporating with the mutual information and image similarity analysis technique for processing the images. The milling test is designed by using Taguchi’s method. The experimental results indicate that the coating layer factor is recognized to make the most significant contribution to the over all performance. The TiAlN-surface multilayer coated inserted blade cutter has the least wear rate amongst these coated milling cutters and has the longest tool life in this experiment.

scholarly journals Implementing a high-efficiency similarity analysis approach for firmware code

PLoS ONE ◽  
2021 ◽  
Vol 16 (1) ◽  
pp. e0245098
Author(s):  
Yisen Wang ◽  
Ruimin Wang ◽  
Jing Jing ◽  
Huanwei Wang
Keyword(s):  
Machine Learning ◽  
High Efficiency ◽  
Control Flow ◽  
Rapid Expansion ◽  
Analysis Approach ◽  
Similarity Analysis ◽  
Basic Block ◽  
Comparison Results ◽  
Flow Features ◽  
Basic Blocks

The rapid expansion of the open-source community has shortened the software development cycle, but the spread of vulnerabilities has been accelerated, especially in the field of the Internet of Things. In recent years, the frequency of attacks against connected devices is increasing exponentially; thus, the vulnerabilities are more serious in nature. The state-of-the-art firmware security inspection technologies, such as methods based on machine learning and graph theory, find similar applications depending on the known vulnerabilities but cannot do anything without detailed information about the vulnerabilities. Moreover, model training, which is necessary for the machine learning technologies, requires a significant amount of time and data, resulting in low efficiency and poor extensibility. Aiming at the above shortcomings, a high-efficiency similarity analysis approach for firmware code is proposed in this study. First, the function control flow features and data flow features are extracted from the functions of the firmware and of the vulnerabilities, and the features are used to calculate the SimHash of the functions. The mass storage and fast query capabilities of the SimHash are implemented by the pigeonhole principle. Second, the similarity function pairs are analyzed in detail within and among the basic blocks. Within the basic blocks, the symbolic execution is used to generate the basic block semantic information, and the constraint solver is used to determine the semantic equivalence. Among the basic blocks, the local control flow graphs are analyzed to obtain their similarity. Then, we implemented a prototype and present the evaluation. The evaluation results demonstrate that the proposed approach can implement large-scale firmware function similarity analysis. It can also get the location of the real-world firmware patch without vulnerability function information. Finally, we compare our method with existing methods. The comparison results demonstrate that our method is more efficient and accurate than the Gemini and StagedMethod. More than 90% of the firmware functions can be indexed within 0.1 s, while the search time of 100,000 firmware functions is less than 2 s.

scholarly journals ENRICH: Exploiting Image Similarity to Maximize Efficient Machine Learning in Medical Imaging

2021 ◽  
Author(s):  
Erin Chinn ◽  
Rohit Arora ◽  
Ramy Arnaout ◽  
Rima Arnaout
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Medical Imaging ◽  
Image Similarity ◽  
Instance Selection ◽  
Computationally Efficient ◽  
Training Set ◽  
Present Evidence ◽  
Medical Expertise ◽  
Efficient Machine

Abstract Deep learning (DL) requires labeled data. Labeling medical images requires medical expertise, which is often a bottleneck. It is therefore useful to prioritize labeling those images that are most likely to improve a model's performance, a practice known as instance selection. Here we introduce ENRICH, a method that selects images for labeling based on how much novelty each image adds to the growing training set. In our implementation, we use cosine similarity between autoencoder embeddings to measure that novelty. We show that ENRICH achieves nearly maximal performance on classification and segmentation tasks using only a fraction of available images, and outperforms the default practice of selecting images at random. We also present evidence that instance selection may perform categorically better on medical vs. non-medical imaging tasks. In conclusion, ENRICH is a simple, computationally efficient method for prioritizing images for expert labeling for DL.

Sign in / Sign up

Export Citation Format

Share Document