SIFT-based Feature Research Articles

A comprehensive guide to content-based image retrieval algorithms with visualsift ensembling.

Content-based image retrieval (CBIR) systems are vital for managing the large volumes of data produced by medical imaging technologies. They enable efficient retrieval of relevant medical images from extensive databases, supporting clinical diagnosis, treatment planning, and medical research. This study aims to enhance CBIR systems' effectiveness in medical image analysis by introducing the VisualSift Ensembling Integration with Attention Mechanisms (VEIAM). VEIAM seeks to improve diagnostic accuracy and retrieval efficiency by integrating robust feature extraction with dynamic attention mechanisms. VEIAM combines Scale-Invariant Feature Transform (SIFT) with selective attention mechanisms to emphasize crucial regions within medical images dynamically. Implemented in Python, the model integrates seamlessly into existing medical image analysis workflows, providing a robust and accessible tool for clinicians and researchers. The proposed VEIAM model demonstrated an impressive accuracy of 97.34% in classifying and retrieving medical images. This performance indicates VEIAM's capability to discern subtle patterns and textures critical for accurate diagnostics. By merging SIFT-based feature extraction with attention processes, VEIAM offers a discriminatively powerful approach to medical image analysis. Its high accuracy and efficiency in retrieving relevant medical images make it a promising tool for enhancing diagnostic processes and supporting medical research in CBIR systems.

An Implementation of Copy-Move Forgery Detector using SIFT-based Feature Refinement

This paper deals with refining the SIFT-based feature set for the Copy-Move forgery detection in image forensics. Many researchers attempt to extract the feature with advanced performance; however, high-dimensional feature sets increment the calculation cost and the detection time. For this reason, we intend to design a simple feature yet have good copy-move forgery detection performance. In addition to that, for various conditions of images, we extract the refined SIFT-based features of robust yet straightforward features applied to Copy-Move image forensics using only the SIFT features that have excellent invariance maintenance. In a Copy-Move forgery image, a definition has a similar distance and slope between a copy and move area. This paper proposed a new scheme for a Copy-Move forgery detection to satisfy the purpose. As a result, the Copy-Move area is detected with 97.8% upper. Thus, the detection ratio is confirmed as an

SIFT-based iris recognition revisited: prerequisites, advantages and improvements

Scale-invariant feature transform (SIFT), which represents a general purpose image descriptor, has been extensively used in the field of biometric recognition. Focusing on iris biometrics, numerous SIFT-based schemes have been presented in past years, offering an alternative approach to traditional iris recognition, which are designed to extract discriminative binary feature vectors based on an analysis of pre-processed iris textures. However, the majority of proposed SIFT-based systems fails to maintain the recognition accuracy provided by generic schemes. Moreover, traditional systems outperform SIFT-based approaches with respect to other key system factors, i.e. authentication speed and storage requirement. In this work, we propose a SIFT-based iris recognition system, which circumvents the drawbacks of previous proposals. Prerequisites, derived from an analysis of the nature of iris biometric data, are utilized to construct an improved SIFT-based baseline iris recognition scheme, which operates on normalized enhanced iris textures obtained from near-infrared iris images. Subsequently, different binarization techniques are introduced and combined to obtain binary SIFT-based feature vectors from detected keypoints and their descriptors. On the CASIAv1, CASIAv4-Interval and BioSecure iris database, the proposed scheme maintains the performance of different traditional systems in terms of recognition accuracy as well as authentication speed. In addition, we show that SIFT-based features complement those extracted by traditional schemes, such that a multi-algorithm fusion at score level yields a significant gain in recognition accuracy.

Joint feature extraction technique for text detection from natural scene image

Detection text detection and extraction from natural scenes (i.e. video or images) can deliver significant information for various applications. To address the issue of text detection, a novel approach for text detection from natural scene image is introduced by developing a joint feature extraction method by considering shape and scale invariant feature transform (SIFT) feature analysis techniques. Shape extraction is improved by applying curvature-based shape analysis model. To construct the feature descriptor, input image is passed through canny edge detection process in which gradients are computed of each image. Later, we perform SIFT analysis and SIFT-based feature matching to formulate the SIFT feature descriptor. Finally, these two descriptors are merged together, and a combined descriptor is presented for text detection. Experimental study is carried out by considering benchmark ICDAR 2003, 2013 and 2015 data sets. Experimental study shows that proposed approach outperforms when compared with state-of-art text detection model.

A novel watermarking for DIBR 3D images with geometric rectification based on feature points

Depth-image-based rendering (DIBR) has become an important technology in 3D displaying with its great advantages. As a result, more and more 3D products copyright problems turn out. Since either the center view with depth image or the synthesized virtual views could be illegally distributed, we need to protect not only the center views but also the synthesized virtual views. In this paper, a robust watermarking method for DIBR 3D images is proposed. After applying three-level DWT to the center image, we utilize spread spectrum technology to embed the watermark into suitable coefficients of the sub-blocks of the center image, by this way we make our method robust to typical signal distortions, such as JPEG compression, noise addition and median filter. Meanwhile, in order to make the proposed method robust to some common geometric distortion attacks, SIFT-based feature points are used for geometric rectification to eliminate the effect caused by geometric distortion attacks. As the experimental results shown, the proposed method is much more robust to the common signal distortion attacks with lower BER (bit error rate) compared with existing methods. With geometric rectification, our method also performs good robustness to some simple affine transformations. In addition, the proposed watermarking method also has good robustness to the common operations of DIBR processing system.

Mapping surgical fields by moving a laser-scanning multimodal scope attached to a robot arm.

Endoscopic visualization in brain tumor removal is challenging because tumor tissue is often visually indistinguishable from healthy tissue. Fluorescence imaging can improve tumor delineation, though this impairs reflectance-based visualization of gross anatomical features. To accurately navigate and resect tumors, we created an ultrathin/flexible, scanning fiber endoscope (SFE) that acquires reflectance and fluorescence wide-field images at high-resolution. Furthermore, our miniature imaging system is affixed to a robotic arm providing programmable motion of SFE, from which we generate multimodal surface maps of the surgical field. To test this system, synthetic phantoms of debulked tumor from brain are fabricated having spots of fluorescence representing residual tumor. Three-dimension (3D) surface maps of this surgical field are produced by moving the SFE over the phantom during concurrent reflectance and fluorescence imaging (30Hz video). SIFT-based feature matching between reflectance images is implemented to select a subset of key frames, which are reconstructed in 3D by bundle adjustment. The resultant reconstruction yields a multimodal 3D map of the tumor region that can improve visualization and robotic path planning. Efficiency of creating these 3D maps is important as they are generated multiple times during tumor margin clean-up. By using pre-programmed motions of the robot arm holding the SFE, the computer vision algorithms are optimized for efficiency by reducing search times. Preliminary results indicate that the time for creating these multimodal maps of the surgical field can be reduced to one third by using known trajectories of the surgical robot moving the image-guided tool.

A Correspondence Search Technique for Geometric Correction of Projected Images

This paper presents a technique for correspondence search between projector and camera images using SIFT (Scale-Invariant Feature Transform) and POC (Phase-Only Correlation). The correspondence search is a key task for camera-based geometric correction of projected imagery. In conventional methods, the correspondence is obtained by projecting the structured light on a projector screen. This paper proposes a geometric correction technique where we use only one snapshot of ordinary video sequences to find projector-camera correspondence. We adopt (i) SIFT-based feature matching to estimate an approximate homography between projector and camera images with a limited number of corresponding points and (ii) POC-based dense sub-pixel correspondence search to adjust precise position of corresponding points. Through a set of experiments, we demonstrate that the proposed technique achieves high-accuracy geometric correction, even if significant brightness change is observed between the original video content to be projected and the real projector image captured by a camera.