REAL-TIME DEPTH MAP ESTIMATION FROM INFRARED STEREO IMAGES OF RGB-D CAMERAS

RGB-D cameras are novel sensing systems that can rapidly provide accurate depth information for 3D perception, among which the type based on active stereo vision has been widely used. However, there are some problems exiting in use, such as the short measurement range and incomplete depth maps. This paper presents a robust and efficient matching algorithm based on semi-global matching to obtain more complete and accurate depth maps in real time. Considering characteristics of captured infrared speckle images, the Gaussian filter is performed firstly to restrain noise and enhance the relativity. It also adopts the idea of block matching for reliability, and a dynamic threshold selection of the block size is used to adapt to various situation. Moreover, several optimizations are applied to improve precision and reduce error. Through experiments on the Intel Realsense R200, the excellent capability of our proposed method is verified.

AdvisOnt: Semantization of Agricultural Advisory Services for Validation of Outcomes of Non-Formal and Informal Learning. I

We propose an advisory system AdvisOnt that analyses the outcomes of non-formal and informal learning and ensures their validation for more efficient matching of information about potential employees, employers and agricultural educational resources. AdvisOnt is based on ontological representation of this knowledge formalized by competencies, vacancies, training courses, user profiles, etc. The system is aimed to generate recommendations for employment or further learning of necessary competencies by matching these objects. External knowledge bases are used for semantic formalization of vacancies and resumes for their more pertinent matching with the help of agricultural domain knowledge and competence classifications. AdvisOnt users receive recommendations on employment and about training courses that provide advisable competencies.

On the Optimal Design of a Bipartite Matching Queueing System

Designing Fair and Efficient Matching Service Systems

The impact of university reputation on employment opportunities: Experimental evidence from Bolivia

Higher education enrolment and graduation rates have increased rapidly inter-generationally across much of the world, offering employers the promise of more knowledgeable recruits and promising individuals new means of social advancement. In the case of Bolivia, the labour force is becoming more heterogeneous over time, which could imply positive effects induced by a closer match between labour supply and recruiters’ needs. However, we show that this is not the case. We revisit the transition mechanisms from college to the workplace, positing recruiters’ interpretations of educational credentials as a crucial determining factor for employability in the formal sector. In a two-branch correspondence study, 2848 fictitious CVs were sent to 1424 formal firms in the three main urban Bolivian areas. We find a large university reputation premium. Applicants from well-valued universities are around 40% more likely to receive a positive response – a 2.25 percentage point advantage from a 7.87% baseline likelihood. Thus, the increasingly heterogeneous labour force is generating additional informational frictions in the labour market, rather than promoting a more efficient matching process. JEL Codes: I25, J24, C93

Inner Knuckle Print Identification Using Artificial Neural Network

A inner knuckle print identification system has been designed and developed. This work presents a new approach to authenticate people according to their finger textures. This proposed method consists of three stages. They are preprocessing, feature extraction and matching. In the first stage, noise is suppressed using an image filtering. In the second stage, features are extracted by local line binary pattern. Artificial neural network and support vector machine are used to provide an efficient matching algorithm for inner knuckle print authentication. After matching, the algorithm returns the best match for the given fingerprint parameters. The use of inner knuckle print in biometric identification has been the most widely used authentication system. A classification with an accuracy of 89% and 97% has been obtained by support vector machine and artificial neural network classifier.