A hybrid content based image retrieval system using log-gabor filter banks

Madhavi, D.; Mohammed, Khwaja Muinuddin Chisti; Jyothi, N.; Patnaik, M. Ramesh

doi:10.11591/ijece.v9i1.pp237-244

Cited by 7 publications

(4 citation statements)

References 11 publications

(14 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various statistical analysis methods and histograms of pixel values are used in [ 15 ]. Furthermore, the use of Gabor filters and genetic algorithms has been demonstrated in several studies [ 16 , 17 , 18 ]. A retrieval approach in the field of remote sensing is presented in [ 19 , 20 ].…”

Section: Related Workmentioning

confidence: 99%

Unsupervised Content Mining in CBIR: Harnessing Latent Diffusion for Complex Text-Based Query Interpretation

Gopu,

Dunna

2024

J. Imaging

View full text Add to dashboard Cite

The paper demonstrates a novel methodology for Content-Based Image Retrieval (CBIR), which shifts the focus from conventional domain-specific image queries to more complex text-based query processing. Latent diffusion models are employed to interpret complex textual prompts and address the requirements of effectively interpreting the complex textual query. Latent Diffusion models successfully transform complex textual queries into visually engaging representations, establishing a seamless connection between textual descriptions and visual content. Custom triplet network design is at the heart of our retrieval method. When trained well, a triplet network will represent the generated query image and the different images in the database. The cosine similarity metric is used to assess the similarity between the feature representations in order to find and retrieve the relevant images. Our experiments results show that latent diffusion models can successfully bridge the gap between complex textual prompts for image retrieval without relying on labels or metadata that are attached to database images. This advancement sets the stage for future explorations in image retrieval, leveraging the generative AI capabilities to cater to the ever-evolving demands of big data and complex query interpretations.

show abstract

Section: Related Workmentioning

confidence: 99%

Unsupervised Content Mining in CBIR: Harnessing Latent Diffusion for Complex Text-Based Query Interpretation

Gopu,

Dunna

2024

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Many works dealing with fingerprint verification task is present in recent years [2], [3], [6]- [8], [10]- [12], [15], [18], [20], [28], [29], [34], [37]- [39], [41], [44]- [47], [57], [58], [63]- [89]. Kommini et al [63] and Sharma et al [72] presented a method of fingerprint recognition based on fractal features extracted of the separated image.…”

Section: Introductionmentioning

confidence: 99%

User identification system for inked fingerprint pattern based on central moments

Baker

Alazawi

Ahmed

et al. 2021

IJEECS

View full text Add to dashboard Cite

The <span>use of the fingerprint recognition has been and remains very important in many security applications and licensing systems. Fingerprint recognition is required in many areas such as licensing access to networks, corporate computers and organizations. In this paper, the system of fingerprint recognition that can be used in several cases of fingerprint such as being rounded at an angle by a randomly inked fingerprint on paper. So, fingerprint image is tooked at a different angle in order to identify the owner of the ink fingerprint. This method involves two working levels. The first one, the fingerprint pattern's shape features are calculated based on the central moments of each image being listed on a regular basis with three states rotation. Each image is rotated at a specified angle. In the second level, the fingerprint holder entered is identified using the previously extracted shape features and compared to the three local databases content of three rotation states. When applied the method for several persons by taken their inked fingerprint on the paper, the accuracy of the system in identifying the owner of the fingerprint after rotation states were close to 83.71.</span>

show abstract

“…GLCM features [3] used in existing retrieval systems are shown to be having low average recall and average precision rate. This can be used further improved using hybrid methods [4]. Content based image retrieval (CBIR) also known as query by image and video content (QBIC) is basically used to search digital images present in large databases.…”

Section: Introductionmentioning

confidence: 99%

Composite Method for Image Retrieval

Madhavi,

Jyothi,

Chisti

2020

IJEAT

Self Cite

View full text Add to dashboard Cite

In the present day to day life the retrieval of images from the larger database has become important like Google search. Presently, CBIR is trending method. In this paper images are retrieved in three stages with color, texture and shape feature extracted in each respective stage. The color feature extraction is done through finding different parameters for an RGB image, combined texture feature extraction through Gray level co-occurrence matrix GLCM and Gabor filter and shape feature extraction through region growing. The experiment is done on images present in coral database. The simulation results have been compared and it has been shown that the proposed method show high retrieval rate in terms of the average precision and average recall.

show abstract

A hybrid content based image retrieval system using log-gabor filter banks

Cited by 7 publications

References 11 publications

Unsupervised Content Mining in CBIR: Harnessing Latent Diffusion for Complex Text-Based Query Interpretation

Unsupervised Content Mining in CBIR: Harnessing Latent Diffusion for Complex Text-Based Query Interpretation

User identification system for inked fingerprint pattern based on central moments

Composite Method for Image Retrieval

Contact Info

Product

Resources

About