Pattern Recognition

Chest X-ray image

This code provides a demonstration of CDF-TS in Matlab.

Classification results for the different datasets with 5% labeled samples

The validity of the fitting algorithm is verified from four aspects

For this demo, we only provide the .p file of our core algorithm, the complete source file (.m) will be released on my personal website (http://www.escience.cn/people/zhengjianwei/index.html) soon after the review period. run Runit.m for the results.

The software developed by MATLAB is able to demostrate infrared and visible image registration using ehanced affine transformation.

Description: The dataset consists of of a large number of realistic synthetic images that feature a number of objects on a table-top, of three classes: staplers, mugs and bananas. These are taken at a variety of lighting, viewpoint and object configuration conditions. In addition, the dataset includes a set of annotated real images that were manually taken to feature a number of objects of the considered classes. The dataset includes over 22000 realistic synthetic images that can be used for training and testing, and 135 annotated real images for testing. All datasets include object annotations and their masks. Image resolution is 256 x 256. Synthetic datasets include all the latent variables of the 3D scene (scene graph). The synthetic scenes were rendered using the Blender software: www.blender.org. For each object its associated latent variables are its position, scaling factor, azimuthal rotation, shape (1-of-K encoding) and colour (RGB). The ground plane has a random RGB colour. The camera is taken to be at a random height above the origin and to be looking down with a random angle of elevation. The illumination model is uniform lighting plus a directional source (specified by the strength, azimuth and elevation of the source). Real dataset: for each object we annotated its class, instance mask, and the contact point using the LabelMe software.

Data used in this paper, more details can be seen http://archive.ics.uci.edu/ml/datasets.html

We propose a new method to characterize mirror-symmetry in open and closed curves represented by means of the Slope Chain Code. This representation is invariant under scale, rotation, and translation. The proposed method allows the classification of symmetrical and asymmetrical contours. It also introduces a measure to quantify the degree of symmetry in quasi-mirror-symmetrical objects. Furthermore, it allows the identification of multiple symmetry axes and their location. The proposed algorithm provides properties such as: global, local, and multiple axes’ detection, as well as the capability to classify symmetrical objects.

LabelProp is a tool that provides a semi-automated method to segment 3D medical images with multiple labels. It is a convenient implementation of our peer-reviewed method designed to assist medical professionals in segmenting musculoskeletal structures on scans based on a small number of annotated slices. LabelProp leverages deep learning techniques, but can be used without a training set. It is available as a PyPi package and offers both a command-line interface (CLI) and an API. Additionally, LabelProp provides two plugins, namely 'napari-labelprop' and 'napari-labelprop-remote', which facilitate training and inference on a single scan within the multi-dimensional viewer Napari.