Ivan Vidović

Crop row detection by global energy minimization

This paper presents a new efficient method for crop row detection which uses a dynamic programming technique to combine image evidence and prior knowledge about the geometric structure which is searched for in the image. The proposed approach consists of three steps, i.e., (i) vegetation detection, (ii) detection of regular patterns, and (iii) determining an optimal crop model. The method is capable of accurately detecting both straight and curved crop rows. The proposed approach is experimentally evaluated on a set of 281 real-world camera images of crops of maize, celery, potato, onion, sunflower and soybean. The proposed approach is compared to two Hough transform based methods and one method based on linear regression. The methods are compared using a novel approach for evaluation of crop row detection methods. The experiments performed demonstrate that the proposed method outperforms the other three considered methods in straight crop row detection and that it is capable of detecting curved crop rows accurately.

Technology transfer of computer vision defect detection to ceramic tiles industry

Visual inspection is carried out manually in ceramic tile industry in Croatia using specially trained and skilled workers. Currently in industry biscuit and crude tiles are not visually inspected for defects. Fatigue, illness and other subjective factors significantly influence workers percentage of found defects and classification quality. In this paper we present a prototype computer vision station (CVS) for real-time biscuit tile defects detection. CVS is a result of an FP7 project. Prototype is mounted on a production conveyor line before the kiln. MFC (Microsoft Foundation Class) based GUI application is created and all developed algorithms are implemented in C++ language using OpenCV and Nvidia CUDA libraries. System hardware is based on core i7 CPU and Nvidia GTX960 GPU. Preliminary results show maximum execution time below 900 ms and defect detection efficiency of 98%.

A new fast fuzzy partitioning algorithm

A new fast fuzzy partitioning algorithm is proposed.The algorithm is able to find a fuzzy globally optimal partition.The algorithm is able to estimate the most appropriate number of clusters. In this paper, a new fast incremental fuzzy partitioning algorithm able to find either a fuzzy globally optimal partition or a fuzzy locally optimal partition of the set A ? R n close to the global one is proposed. This is the main impact of the paper, which could have an important role in applied research. Since fuzzy k-optimal partitions with k = 2 , 3 , ? , k m a x clusters are determined successively in the algorithm, it is possible to calculate corresponding validity indices for every obtained partition. The number kmax is defined in such a way that the objective function value of optimal partition with kmax clusters is relatively very close to the objective function value of optimal partition with ( k m a x - 1 ) clusters. Before clustering, the data are normalized and afterwards several validity indices are applied to partitions of the normalized data. Very simple relationships between used validity indices on normalized and original data are given as well. Hence, the proposed algorithm is able to find optimal partitions with the most appropriate number of clusters. The algorithm is tested on numerous synthetic data sets and several real data sets from the UCI data repository.

A nearest neighbor approach for fruit recognition in RGB-D images based on detection of convex surfaces

Abstract Automatic fruit picking is a challenging problem in robotics with a wide application field. A prerequisite for realization of a robotic fruit picker is its ability to detect fruits in tree tops. An expert system, which would be able to compete with human perception, must be capable of recognizing fruits among leaves and branches under uncontrolled conditions, where fruits are occluded and shaded. In this paper, a novel approach for fruit recognition in RGB-D images based on detection and classification of convex surfaces is proposed. The input RGB-D image is first segmented into convex surfaces by a region growing procedure. Each convex surface is then described by an appropriate descriptor and classified with the aid of the associated descriptor. A novel descriptor of approximately convex surfaces is proposed, which we named Convex Template Instance (CTI) descriptor. It is based on approximating surfaces by convex polyhedrons with quantized face orientations, where every polyhedron face corresponds to one descriptor component. Computation of the proposed descriptor is simple and can be performed very efficiently. The proposed CTI descriptor is compared to the SHOT descriptor, a standard descriptor for 3D point clouds. Two variants of the both CTI and SHOT descriptor are evaluated, a variant which uses color and a variant which does not. A k-nearest neighbor classifier is used to classify detected surfaces into two classes: fruit and other. The main advantage of the proposed expert system in comparison to other fruit recognition solutions is its computational efficiency, which is of great importance for its target application – an automatic fruit picker. The proposed approach is evaluated using a challenging dataset containing RGB-D images of four fruit sorts acquired under uncontrolled conditions, which has been made publicly available to the scientific community, allowing benchmarking of novel fruit recognition methods.

Semi-automatic prototype system for bacterial colony counting

Bacterial colony forming unit (CFU) counting is a tedious task mostly done by humans. Procedure is error prone, time-consuming and laborious. In this paper we present a semi-automatic prototype system for CFU counting. The developed prototype consist of a hardware (area scan camera with LED light source) and C#-based desktop application. The application enables manual, semi-automatic and automatic CFU counting. Automatic CFU counting is based on Hough transform for circles. Obtained results can be user-corrected for better accuracy. In the experimental analysis, the developed application is evaluated on the synthetic CFU images. The results include time and counting performance measurements compared with the manual count. The results show that semi-automatic counting procedure can save on average 45% of counting time compared to manual count with the same counting accuracy. The automatic CFU counting on average has precision of 97% and recall of 82%.