Speeded Up Robust Features Key Points Research Articles

A Deep Learning Model to Inspect Image Forgery on SURF Keypoints of SLIC Segmented Regions

Copy-Move Forgery (CMF) is a common form of image manipulation attack that involves copying and pasting a part of an image to another position within the same image. This study proposes a Deep Learning (DL) model for detecting CMF, particularly in the presence of various malicious attacks. The proposed approach involves several steps, including converting the input image to grayscale, preprocessing the image using the Simple Linear Iterative Clustering (SLIC) algorithm to generate superpixel partitions, and then extracting keypoint features using the Speeded Up Robust Features (SURF) detector. Finally, a Generative Adversarial Network (GAN) is employed for feature description and matching. To assess the effectiveness of the approach, the types of features used for copy-move forgery were addressed. The proposed approach was examined under rotation, blurring, jpg compression, and scaling attacks. Furthermore, experimental results showed that the proposed approach can detect multiple CMFs with high accuracy. Finally, the proposed method was compared with recent state-of-the-art methods.

Target recognition method on retina-like laser detection and ranging images.

A target recognition method on retina-like laser detection and ranging images is proposed in this study. The method does not require complicated image preprocessing due to speeded-up robust features (SURF) combined with retina-like sampling as feature match descriptors. Subpixel resampling achieves optimization and avoids affecting the accuracy and precision of target recognition. Several experiments are conducted to analyze the validity of SURF directly. The separate exploration of SURF with Cartesian, log-polar (LP), and inverse LP images are discussed. Furthermore, examples are used to demonstrate the capability of the proposed method. Finally, important conclusions are drawn as follows. (I) SURF extraction becomes difficult when it is directly used in LP images as expected. (II) Applying SURF with an inverse LP process is valid. (III) SURF key match points in inverse LP images are less than those in Cartesian images. (IV) The accuracy of the proposed solution agrees well with that of the Cartesian solution when angle and scale variants are used. The present recognition solution may be used in various applications involving space-variant image processing.

Discrimination of Common Ragweed (Ambrosia artemisiifolia)and Mugwort (Artemisia vulgaris)Based on Bag of Visual Words Model

Common ragweed is a plant species causing allergic and asthmatic symptoms in humans. To control its propagation, an early identification system is needed. However, due to its similar appearance with mugwort, proper differentiation between these two weed species is important. Therefore, we propose a method to discriminate common ragweed and mugwort leaves based on digital images using bag of visual words (BoVW). BoVW is an object-based image classification that has gained acceptance in many areas of science. We compared speeded-up robust features (SURF) and grid sampling for keypoint selection. The image vocabulary was built using K-means clustering. The image classifier was trained using support vector machines. To check the robustness of the classifier, specific model runs were conducted with and without damaged leaves in the trainings dataset. The results showed that the BoVW model allows the discrimination between common ragweed and mugwort leaves with high accuracy. Based on SURF keypoints with 50% of 788 images in total as training data, we achieved a 100% correct recognition of the two plant species. The grid sampling resulted in slightly less recognition accuracy (98 to 99%). In addition, the classification based on SURF was up to 31 times faster.

Keypoint based automatic image orientation and skew investigation on tie points

PurposeThe relative orientation (RO) is an important step on photogrammetric processes of stereoscopic images. The relationship between the stereoscopic images is constructed by tie (conjugate) points. Many automatic tie point selection methods have been introduced by photogrammetry community so far. The scale invariant feature transform (SIFT) and speeded‐up robust features (SURF) are frequently used for automatic tie point selection from stereoscopic images. However, any research has been performed related to RO errors (y‐parallaxes) on SIFT and SURF extracted tie points. The purpose of this paper is to compute errors on tie points and investigate their distributions on the model area in terms of size.Design/methodology/approachThe experimental studies were performed on an historical building as it enables more tie points for investigation. While a couple of the stereoscopic images include rich details, the other has poor details. The image orientation and tie point selection accuracy were evaluated by root mean square and y‐parallaxes, respectively. The relationship between y‐parallaxes of tie points and their distances from centre of the images were investigated.FindingsSIFT and SURF have a large number of tie points according to manual method. The y‐parallaxes on tie points have uniform distribution for two methods. There are relations between the precision of the SIFT and SURF keypoints and their distances from the centre of the image. Moreover, the accuracy of the RO and size of the y‐parallaxes on tie points depend on matching accuracy of the keypoints. Furthermore, although there are a few tie points that have large y‐parallax especially by the SURF, RO could be performed with high accuracy thanks to numerous tie points.Originality/valueStereoscopic images of close‐range photogrammetry have different scale and rotations, unlike aerial photogrammetry. Manual selection of tie points is time consuming and tedious. Furthermore, if the measurement surface has no implicit entities, enough tie points from the images cannot be selected by manually. However, tie point selection can be performed by SIFT and SURF automatically, even if there are scale, noise and rotation between the images.

Visual tracking and learning using speeded up robust features

A speeded up robust features (SURF) based optical flow algorithm is presented for visual tracking in real scenarios. SURF construct invariant features to correspond the blobs of interest across frames. Meanwhile, new feature-based optical flow algorithm is used to compute the warp matrix of a region centered on SURF key points. Furthermore, on-line visual learning for long-term tracking is performed using incremental object subspace method, which includes the correct update of the sample mean and appearance model. The proposed SURF based tracking and learning method contributes measurably to improving overall tracking performance. Experimental work demonstrates that the proposed strategy improves the performance of the classical optical flow algorithms in complicated real scenarios.

Influence of Confocal Scanning Laser Microscopy specific acquisition parameters on the detection and matching of Speeded-Up Robust Features

The robustness and distinctiveness of local features to various object or scene deformations and to modifications of the acquisition parameters play key roles in the design of many computer vision applications. In this paper we present the results of our experiments on the behavior of a recently developed technique for local feature detection and description, Speeded-Up Robust Features (SURF), regarding image modifications specific to Confocal Scanning Laser Microscopy (CSLM). We analyze the repeatability of detected SURF keypoints and the precision–recall of their matching under modifications of three important CSLM parameters: pinhole aperture, photomultiplier (PMT) gain and laser beam power. During any investigation by CSLM these three parameters have to be modified, individually or together, in order to optimize the contrast and the Signal Noise Ratio (SNR), being also inherently modified when changing the microscope objective. Our experiments show that an important amount of SURF features can be detected at the same physical locations in images collected at different values of the pinhole aperture, PMT gain and laser beam power, and further on can be successfully matched based on their descriptors. In the final part, we exemplify the potential of SURF in CSLM imaging by presenting a SURF-based computer vision application that deals with the mosaicing of images collected by this technique.