Image Pair Comparison for Near-duplicates Detection

Gorokhovatskyi, Oleksii; Peredrii, Olena

doi:10.47839/ijc.22.1.2879

Cited by 4 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main drawback of previous research is the lack of experiments, the main idea and application prototype were tested only, making it difficult to understand whether the common idea is scalable. Our other research [16] about using image feature descriptors for the detection of near-duplicate images helped us to understand some nuances for the usage of descriptors in practical applications.…”

Section: Related Workmentioning

confidence: 99%

Medoids as a Packing of Orb Image Descriptors

Gorokhovatskyi,

Yakovleva

2024

A.I.S.

View full text Add to dashboard Cite

The aim of the research. The paper presents the research about the feasibility to use matching medoids obtained from the set of ORB descriptors instead matching the full set of binary descriptors for image classification problem. Research results. Different methods that include direct brute force medoids matching, grouping of medoids for separate classes, and grouping of descriptors followed by calculation of medoids amongst them were proposed. Numerical experiments were performed for all these methods in order to compare the classification accuracy and inference time. It has been shown that using of medoids allowed us to redistribute processing time in order to perform more calculations during preprocessing rather than during classification. According to modelling performed on the Leeds Butterly dataset matching images based on medoids could have the same accuracy as matching of descriptors (0.69–0.88 for different number of features). Medoids require additional time for the calculation during preprocessing stage but classification time becomes faster: in our experiments we have obtained about 9–10 times faster classification and same 9–10 times increasing preprocessing time for the models that have comparable accuracies. Finally, the efficiency of the proposed ideas was compared to the CNN trained and evaluated on the same data. As expected, CNN required much more preprocessing (training) time but the result is worth it: this approach provides the best classification accuracy and inference time. Conclusion. Medoids matching could have the same accuracy as direct descriptors matching, but the usage of medoids allows us to redistribute the overall modeling time with the increasing preprocessing time and making inference faster.

show abstract

Section: Related Workmentioning

confidence: 99%

Medoids as a Packing of Orb Image Descriptors

Gorokhovatskyi,

Yakovleva

2024

A.I.S.

View full text Add to dashboard Cite

show abstract

“…In structural methods of image classification, the description 𝑍 of a visual object is presented in the form of a finite set 𝑍 = {𝑍 } of 𝑠 key points of the descriptors (KP). The descriptor 𝑧 is a numerical vector of dimension 𝑛 [6,10,29]. The descriptions of the object and etalons are finite sets of multidimensional vectors.…”

Section: Problem Statementmentioning

confidence: 99%

“…Researchers note that with significant dimensions of the feature space (more than 20), even search systems based on the sufficiently developed structures -trees lose their effectiveness [12,16]. At the same time, the means of establishing the equivalence of images on the basis of structural information, implemented on applied datasets, proved their effectiveness even when using a small subset of the description [20,29].…”

Section: Literature Reviewmentioning

confidence: 99%

Accelerating Image Classification based on a Model for Estimating Descriptor-to-Class Distance

Gorokhovatskyi,

Gadetska,

Stiahlyk

2023

IJC

View full text Add to dashboard Cite

The article describes a method of image classification based on the estimation of the distance to the etalon class. The implementation of estimates gives a significant gain in classification speed compared to linear search while maintaining a decent level of accuracy. The methodology is based on the use of the triangle inequality for images given by a set of binary vectors as descriptors of the image key points. The evaluation is applied to the "object descriptor – etalon" classification method, which is based on the descriptor voting procedure. An analysis of evaluation options is carried out using the parameters of the etalon sets in the form of a medoid and the closest or farthest points from it. The gain in classification time compared to the traditional method proportionally depends on the number of descriptors in the etalon description. Software simulation of classifiers with the implementation of evaluation shows a gain in speed of 350-450 times for the description of 500 descriptors while maintaining one hundred percent classification accuracy on the training set of similar NFT images. A control sample experiment shows that the classifier with estimation can respond better to image details compared to the traditional method.

show abstract