An Effective Content Based Image Retrieval Using Multi Feature Fusion Algorithm with Optimized Retrieval Technique of Soft Computing Approach
Bibliographic record
Abstract
With the increasing digitization of healthcare, hospitals generate and store thousands of medical images daily, creating large-scale datasets that demand efficient retrieval solutions. Content-Based Image Retrieval (CBIR) systems address this by identifying relevant images based on visual features rather than textual metadata. While various CBIR approaches exist, many suffer from low precision, redundant retrievals, and slow query processing times. This paper introduces a novel hybrid CBIR framework that significantly improves retrieval accuracy and efficiency by integrating Principal Component Analysis (PCA) for texture extraction, Wavelet Transform (WT) for shape feature extraction, and Canonical Correlation Analysis (CCA) for advanced feature fusion. Unlike previous methods that rely on single-feature analysis or basic fusion strategies, our approach combines multiple complementary features into a unified representation, enhancing the system's ability to discern subtle patterns in medical images. CCA helps to find features from the medical images that are maximally related, e.g., the part of the breast that usually co-occur when someone is under observation. Additionally, we apply a customized classification strategy using Fuzzy Support Vector Machine optimized with Modified Whale Optimization Algorithm (FSVM-MWOA), which enhances model adaptability and retrieval precision. FSVM a variant of SVM that incorporates fuzzy logic to handle uncertainty and noisy data, MWOA an enhanced version of the bio-inspired Whale Optimization Algorithm, used here to optimize the parameters of the FSVM. Experimental results show that the proposed system achieves over 90% retrieval accuracy, reduces query response time by up to 40%, and minimizes redundancy, outperforming conventional CBIR techniques. This integrated approach not only addresses the limitations of existing methods but also introduces a scalable and robust solution tailored to the specific challenges of medical image datasets.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".