6533b85dfe1ef96bd12be991

RESEARCH PRODUCT

2D/3D Object Recognition and Categorization Approaches for Robotic Grasping

El Houssine BouyakhfHaris Ahmad KhanMohamed HannatNabila Zrira

subject

0209 industrial biotechnologyComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONCognitive neuroscience of visual object recognition[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]02 engineering and technology[ INFO.INFO-CV ] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Color quantizationDeep belief network[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]ComputingMethodologies_PATTERNRECOGNITION020901 industrial engineering & automationCategorizationBag-of-words modelHistogram0202 electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionArtificial intelligenceCluster analysisbusinessClassifier (UML)

description

International audience; Object categorization and manipulation are critical tasks for a robot to operate in the household environment. In this paper, we propose new methods for visual recognition and categorization. We describe 2D object database and 3D point clouds with 2D/3D local descriptors which we quantify with the k-means clustering algorithm for obtaining the Bag of Words (BOW). Moreover, we develop a new global descriptor called VFH-Color that combines the original version of Viewpoint Feature Histogram (VFH) descriptor with the color quantization histogram, thus adding the appearance information that improves the recognition rate. The acquired 2D and 3D features are used for training Deep Belief Network (DBN) classifier. Results from our experiments for object recognition and categorization show an average of recognition rate between 91% and 99% which makes it very suitable for robot-assisted tasks.

https://doi.org/10.1007/978-3-319-63754-9_26