Image retrieval of wool fabric. Part III: based on aggregated convolutional descriptors and approximate nearest neighbors search

For sample reproduction, texture and color are both significant when the consumer has no specific or individual demands or cannot describe the requirements clearly. In this paper, an effective method based on aggregated convolutional descriptors and approximate nearest neighbors search was proposed to combine the texture and color feature for wool fabric retrieval. Aggregated convolutional descriptors from different layers were combined to characterize the wool fabric image. The approximate nearest neighbors search method Annoy was adopted for similarity measurement to balance the trade-off between the search performance and the elapsed time. A wool fabric image database containing 82,073 images was built to demonstrate the efficacy of the proposed method. Different feature extraction and similarity measurement methods were compared with the proposed method. Experimental results indicate that the proposed method can combine the texture and color feature, being effective and superior for image retrieval of wool fabric. The proposed scheme can provide references for the worker in the factory, saving a great deal of labor and material resources.

Metric Spaces with Expensive Distances

In algorithms for finite metric spaces, it is common to assume that the distance between two points can be computed in constant time, and complexity bounds are expressed only in terms of the number of points of the metric space. We introduce a different model, where we assume that the computation of a single distance is an expensive operation and consequently, the goal is to minimize the number of such distance queries. This model is motivated by metric spaces that appear in the context of topological data analysis. We consider two standard operations on metric spaces, namely the construction of a [Formula: see text]-spanner and the computation of an approximate nearest neighbor for a given query point. In both cases, we partially explore the metric space through distance queries and infer lower and upper bounds for yet unexplored distances through triangle inequality. For spanners, we evaluate several exploration strategies through extensive experimental evaluation. For approximate nearest neighbors, we prove that our strategy returns an approximate nearest neighbor after a logarithmic number of distance queries.

Dog Identification Method Based on Muzzle Pattern Image

Currently, invasive and external radio frequency identification (RFID) devices and pet tags are widely used for dog identification. However, social problems such as abandoning and losing dogs are constantly increasing. A more effective alternative to the existing identification method is required and the biometrics can be the alternative. This paper proposes an effective dog muzzle recognition method to identify individual dogs. The proposed method consists of preprocessing, feature extraction, matching, and postprocessing. For preprocessing, proposed resize and histogram equalization are used. For feature extraction algorithm, Scale Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Binary Robust Invariant Scaling Keypoints (BRISK) and Oriented FAST, and Rotated BRIEF (ORB) are applied and compared. For matching, Fast Library for Approximate Nearest Neighbors (FLANN) is used for SIFT and SURF, and hamming distance are used for BRISK and ORB. For postprocessing, two techniques to reduce incorrect matches are proposed. The proposed method was evaluated with 55 dog muzzle pattern images acquired from 11 dogs and 990 images augmented by the image deformation (i.e., angle, illumination, noise, affine transform). The best Equal Error Rate (EER) of the proposed method was 0.35%, and ORB was the most appropriate for the dog muzzle pattern recognition.

Approximate k-nearest neighbors graph for single-cell Hi-C dimensional reduction with MinHash

Single-cell Hi-C interaction matrices are high dimensional and very sparse. To cluster thousands of single-cell Hi-C interaction matrices they are flattened and compiled into one matrix. This matrix can, depending on the resolution, have a few millions or even billions of features and any computation with it is therefore memory demanding. A common approach to reduce the number of features is to compute a nearest neighbors graph. However, the exact euclidean distance computation is in O(n2) and therefore we present an implementation of an approximate nearest neighbors method based on local sensitive hashing running in O(n). The presented method is able to process a 10kb single-cell Hi-C data set with 2500 cells and needs 53 GB of memory while the exact k-nearest neighbors approach is not computable with 1 TB of memory.

Wind turbine tower detection using feature descriptors and deep learning

Wind Turbine Towers (WTTs) are the main structures of wind farms. They are costly devices that must be thoroughly inspected according to maintenance plans. Today, existence of machine vision techniques along with unmanned aerial vehicles (UAVs) enable fast, easy, and intelligent visual inspection of the structures. Our work is aimed towards developing a vision-based system to perform Nondestructive tests (NDTs) for wind turbines using UAVs. In order to navigate the flying machine toward the wind turbine tower and reliably land on it, the exact position of the wind turbine and its tower must be detected. We employ several strong computer vision approaches such as Scale-Invariant Feature Transform (SIFT), Speeded Up Robust Features (SURF), Features from Accelerated Segment Test (FAST), Brute-Force, Fast Library for Approximate Nearest Neighbors (FLANN) to detect the WTT. Then, in order to increase the reliability of the system, we apply the ResNet, MobileNet, ShuffleNet, EffNet, and SqueezeNet pre-trained classifiers in order to verify whether a detected object is indeed a turbine tower or not. This intelligent monitoring system has auto navigation ability and can be used for future goals including intelligent fault diagnosis and maintenance purposes. The simulation results show the accuracy of the proposed model are 89.4% in WTT detection and 97.74% in verification (classification) problems.

Accumulative Errors Optimization for Visual Odometry of ORB-SLAM2 Based on RGB-D Cameras

Oriented feature from the accelerated segment test (oFAST) and rotated binary robust independent elementary features (rBRIEF) SLAM2 (ORB-SLAM2) represent a recognized complete visual simultaneous location and mapping (SLAM) framework with visual odometry as one of its core components. Given the accumulated error problem with RGB-Depth ORB-SLAM2 visual odometry, which causes a loss of camera tracking and trajectory drift, we created and implemented an improved visual odometry method to optimize the cumulative error. First, this paper proposes an adaptive threshold oFAST algorithm to extract feature points from images and rBRIEF is used to describe the feature points. Then, the fast library for approximate nearest neighbors strategy is used for image rough matching, the results of which are optimized by progressive sample consensus. The image matching precision is further improved by using an epipolar line constraint based on the essential matrix. Finally, the efficient Perspective-n-Point method is used to estimate the camera pose and a least-squares optimization problem is constructed to adjust the estimated value to obtain the final camera pose. The experimental results show that the proposed method has better robustness, higher image matching accuracy and more accurate determination of the camera motion trajectory.