Local Shape Descriptors for Neuron Segmentation

We present a simple, yet effective, auxiliary learning task for the problem of neuron segmentation in electron microscopy volumes. The auxiliary task consists of the prediction of Local Shape Descriptors (LSDs), which we combine with conventional voxel-wise direct neighbor affinities for neuron boundary detection. The shape descriptors are designed to capture local statistics about the neuron to be segmented, such as diameter, elongation, and direction. On a large study comparing several existing methods across various specimen, imaging techniques, and resolutions, we find that auxiliary learning of LSDs consistently increases segmentation accuracy of affinity-based methods over a range of metrics. Furthermore, the addition of LSDs promotes affinitybased segmentation methods to be on par with the current state of the art for neuron segmentation (Flood-Filling Networks, FFN), while being two orders of magnitudes more efficient—a critical requirement for the processing of future petabyte-sized datasets. Implementations of the new auxiliary learning task, network architectures, training, prediction, and evaluation code, as well as the datasets used in this study are publicly available as a benchmark for future method contributions.

A Comparative Study of Weighting Methods for Local Reference Frame

In the field of photogrammetric engineering, computer vision, and graphics, local shape description is an active research area. A wide variety of local shape descriptors (LSDs) have been designed for different applications, such as shape retrieval, object recognition, and 3D registration. The local reference frame (LRF) is an important component of the LSD. Its repeatability and robustness directly influence the descriptiveness and robustness of the LSD. Several weighting methods have been proposed to improve the repeatability and robustness of the LRF. However, no comprehensive comparison has been implemented to evaluate their performance under different data modalities and nuisances. In this paper, we focus on the comparison of weighting methods by using six datasets with different data modalities and application contexts. We evaluate the repeatability of the LRF under different nuisances, including occlusion, clutter, partial overlap, varying support radii, Gaussian noise, shot noise, point density variation, and keypoint localization error. Through the experiments, the traits, advantages, and disadvantages of weighting methods are summarized.

Quintuple Local Coordinate Images for Local Shape Description

Owing to poor descriptiveness, weak robustness, and high computation complexity of local shape descriptors (<small>LSDs</small>), point-cloud registration in the case of partial overlap and object recognition in a cluttered environment are still challeng- ing tasks. For this purpose, an <small>LSD</small> is developed in this article by proposing a new local reference frame (<small>LRF</small>) method and designing a novel feature representation. In the <small>LRF</small> method, two weighting methods are applied to obtain robustness to noise, point-density variation, and incomplete shape. Additionally, a vector representation is calculated to disambiguate the sign of the x-axis. The feature representation encodes the local information by generating the local coordinate images from five views. Thus, more geometric and spatial information is included in the descriptor. Finally, the performance of the <small>LRF</small> method and the <small>LSD</small> is evaluated on several popular data sets. The experimental results demonstrate well that the <small>LRF</small> is robust to noise, point-density variation, and incomplete shape, and the <small>LSD</small> holds strong robustness, superior descriptiveness, and high computational efficiency.

Multi-Sensor Face Registration Based on Global and Local Structures

The work reported in this paper aims at utilizing the global geometrical relationship and local shape feature to register multi-spectral images for fusion-based face recognition. We first propose a multi-spectral face images registration method based on both global and local structures of feature point sets. In order to combine the global geometrical relationship and local shape feature in a new Student’s t Mixture probabilistic model framework. On the one hand, we use inner-distance shape context as the local shape descriptors of feature point sets. On the other hand, we formulate the feature point sets registration of the multi-spectral face images as the Student’s t Mixture probabilistic model estimation, and local shape descriptors are used to replace the mixing proportions of the prior Student’s t Mixture Model. Furthermore, in order to improve the anti-interference performance of face recognition techniques, a guided filtering and gradient preserving image fusion strategy is used to fuse the registered multi-spectral face image. It can make the multi-spectral fusion image hold more apparent details of the visible image and thermal radiation information of the infrared image. Subjective and objective registration experiments are conducted with manual selected landmarks and real multi-spectral face images. The qualitative and quantitative comparisons with the state-of-the-art methods demonstrate the accuracy and robustness of our proposed method in solving the multi-spectral face image registration problem.

3D Object Recognition System Based On Local Shape Descriptors and Depth Data Analysis

Background: A physical object, which is actually in 3D form, is captured by a sensor/ camera (in case of computer vision) and seen by a human eye (in case of a human vision). When someone is observing something, many other things are also involved there which make it more challenging to recognize. After capturing such a thing by a camera or sensor, a digital image is formed which is nothing other than a bunch of pixels. It is becoming important to know that how a computer understands images. Objective: This paper is for highlighting novel techniques on 3D object recognition system with local shape descriptors and depth data analysis. Methods: The proposed work is applied to RGBD and COIL-100 datasets and this is of four-fold as preprocessing, feature generation, dimensionality reduction, and classification. The first stage of preprocessing is smoothing by 2D median filtering on the depth (Z-value) and registration by orientation correction on 3D object data. The next stage is of feature generation and having two phases of shape map generation with shape index map and SIFT/SURF descriptors. The dimensionality reduction is the third stage of this proposed work where linear discriminant analysis and principal component analysis are used. The final stage is fused on classification. Results: Here, calculation of the discriminative subspace for the training set, testing of object data and classification is done by comparing target and query data with different aspects for finding proper matching tasks. Conclusion: This concludes with new proposed approach of 3D Object Recognition. The local shape descriptors are used for 3D object recognition system to implement and test. This system is achieves 89.2% accuracy for Columbia object image library-100 images by using local shape descriptors.