Wyniki wyszukiwania - BazTech

1

Semantic hashing for fast solar magnetogram retrieval

Grycuk Rafał, Scherer Rafał, Marchlewska Alina, Napoli Christian

Journal of Artificial Intelligence and Soft Computing Research

|

2022

|

Vol. 12, No. 4

299--306

EN

We propose a method for content-based retrieving solar magnetograms. We use the SDO Helioseismic and Magnetic Imager output collected with SunPy PyTorch libraries. We create a mathematical representation of the magnetic field regions of the Sun in the form of a vector. Thanks to this solution we can compare short vectors instead of comparing full-disk images. In order to decrease the retrieval time, we used a fully-connected autoencoder, which reduced the 256-element descriptor to a 32-element semantic hash. The performed experiments and comparisons proved the efficiency of the proposed approach. Our approach has the highest precision value in comparison with other state-of-the-art methods. The presented method can be used not only for solar image retrieval but also for classification tasks.

2

Robust content-based image retrieval using ICCV, GLCM, and DWT-MSLBP descriptors

Chavda Sagar, Goyani Mahesh

Computer Science

|

2022

|

T. 23 (1)

5--36

EN

Content-based image retrieval (CBIR) retrieves visually similar images from a dataset based on a specified query. A CBIR system measures the similarities between a query and the image contents in a dataset and ranks the dataset images. This work presents a novel framework for retrieving similar images based on color and texture features. We have computed color features with an improved color coherence vector (ICCV) and texture features with a gray-level co-occurrence matrix (GLCM) along with DWT-MSLBP (which is derived from applying a modified multi-scale local binary pattern [MS-LBP] over a discrete wavelet transform [DWT], resulting in powerful textural features). The optimal features are computed with the help of principal component analysis (PCA) and linear discriminant analysis (LDA). The proposed work uses a variancebased approach for choosing the number of principal components/eigenvectors in PCA. PCA with a 99.99% variance preserves healthy features, and LDA selects robust ones from the set of features. The proposed method was tested on four benchmark datasets with Euclidean and city-block distances. The proposed method outshines all of the identified state-of-the-art literature methods.

3

Fast image index for database management engines

Grycuk Rafał, Najgebauer Patryk, Kordos Miroslaw, Scherer Magdalena M., Marchlewska Alina

Journal of Artificial Intelligence and Soft Computing Research

|

2020

|

Vol. 10, No. 2

113--123

EN

Large-scale image repositories are challenging to perform queries based on the content of the images. The paper proposes a novel, nested-dictionary data structure for indexing image local features. The method transforms image local feature vectors into two-level hashes and builds an index of the content of the images in the database. The algorithm can be used in database management systems. We implemented it with an example image descriptor and deployed in a relational database. We performed the experiments on two image large benchmark datasets.

4

Detecting visual objects by edge crawling

Grycuk Rafał, Wojciechowski Adam, Wei Wei, Siwocha Agnieszka

Journal of Artificial Intelligence and Soft Computing Research

|

2020

|

Vol. 10, No. 3

223--237

EN

Content-based image retrieval methods develop rapidly with a growing scale of image repositories. They are usually based on comparing and indexing some image features. We developed a new algorithm for finding objects in images by traversing their edges. Moreover, we describe the objects by histograms of local features and angles. We use such a description to retrieve similar images fast. We performed extensive experiments on three established image datasets proving the effectiveness of the proposed method.

5

Varish N., Kumar S., Pal A. K.

Fundamenta Informaticae

|

2017

|

Vol. 156, nr 2

209--235

EN

Content-based image retrieval (CBIR) scheme has gained popularity in the field of information retrieval for retrieving some relevant images from the image database based on the visual descriptors such as color, texture and/or shape of a given query image. In this paper, color features have been exploited from each color component of an RGB color image by using multiresolution approach since most of the information of an image is undetected at one resolution level while some other undetectable information is visualized in other multi-resolution levels. Initially, Gaussian image pyramid is employed on each color component of the color image and subsequent DCT is computed directly on the obtained multi-resolution image planes. Then some significant DCT coefficients are selected according to the zigzag scanning order. For formation of the feature vector, we have derived some statistical values from AC coefficients and all other DC coefficients are included entirely. Finally, a similarity measure is suggested during image retrieval process and it is found that the overall computation overhead is reduced due to consideration of the proposed similarity measure. The proposed CBIR scheme is validated on a two standard Corel-1K and GHIM-10K image databases and satisfactory results are achieved in terms of precision, recall and F-score. The retrieved results show that the proposed scheme outperforms significantly over other related CBIR schemes.

6

Image Retrieval Based on Text and Visual Content Using Neural Networks

Castro D. A., Seijas L. M.

Journal of Applied Computer Science Methods

|

2010

|

Vol. 2 No. 1

21--39

EN

In the last few years there has been a dramatic increase in the amount of visual data to be searched and retrieved. Typically, images are described by their textual content (TBIR) or by their visual features (CBIR). However, these approaches still present many problems. The hybrid approach was recently introduced, combining both characteristics to improve the benefits of using text and visual content separately. In this work we examine the use of the Self Organizing Maps for content-based image indexing and retrieval. We propose a scoring function which eliminates irrelevant images from the results and we also introduce a SOM variant (ParBSOM) that reduces training and retrieval times. The application of these techniques to the hybrid approach improved computational results.

7

Current challenges in content based image retrieval by means of low-level feature combining

Forczmański P., Frejlichowski D.

Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica

|

2010

|

Vol. 10, no. 1

41--49

EN

The aim of this paper is to discuss a fusion of the two most popular low-level image features - colour and shape - in the aspect of content-based image retrieval. By combining them we can achieve much higher accuracy in various areas, e.g. pattern recognition, object representation, image retrieval. To achieve such a goal two general strategies (sequential and parallel) for joining elementary queries were proposed. Usually they are employed to construct a processing structure, where each image is being decomposed into regions, based on shapes with some characteristic properties - colour and its distribution. In the paper we provide an analysis of this proposition as well as the exemplary results of application in the Content Based Image Retrieval problem. The original contribution of the presented work is related to different fusions of several shape and colour descriptors (standard and non-standard ones) and joining them into parallel or sequential structures giving considerable improvements in content-based image retrieval. The novelty is based on the fact that many existing methods (even complex ones) work in single domain (shape or colour), while the proposed approach joins features from different areas.