Paulus Insap Santosa

A Comparative Experiment of Several Shape Methods in Recognizing Plants

Shape is an important aspects in recognizing plants. Several approaches have been introduced to identify objects, including plants. Combination of geometric features such as aspect ratio, compactness, and dispersion, or moments such as moment invariants were usually used toidentify plants. In this research, a comparative experiment of 4 methods to identify plants using shape features was accomplished. Two approaches have never been used in plants identification yet, Zernike moments and Polar Fourier Transform (PFT), were incorporated. The experimental comparison was done on 52 kinds of plants with various shapes. The result, PFT gave best performance with 64% in accuracy and outperformed the other methods.

FOLIAGE PLANT RETRIEVAL USING POLAR FOURIER TRANSFORM , COLOR MOMENTS AND VEIN FEATURES

This paper proposed a method that combines Polar Fourier Transform, color moments, and vein features to retrieve leaf images based on a leaf image. The method is very useful to help people in recognizing foliage plants. Foliage plants are plants that have various colors and unique patterns in the leaf. Therefore, the colors and its patterns are information that should be counted on in the processing of plant identification. To compare the performance of retrieving system to other result, the experiments used Flavia dataset, which is very popular in recognizing plants. The result shows that the method gave better performance than PNN, SVM, and Fourier Transform. The method was also tested using foliage plants with various colors. The accuracy was 90.80% for 50 kinds of plants.

Sign Language Recognition in Robot Teleoperation using Centroid Distance Fourier Descriptors

in robot teleoperation system can be done in several ways, including the use of sign language. In this paper, the use of centroid distance Fourier descriptors as hand shape descriptor in sign language recognition from visually captured hand gesture is considered. The sign language adopts the American Sign Language finger spelling. Only static gestures in the sign language are used. To obtain hand images, depth imager is used in this research. Hand image is extracted from depth image by applying threshold operation. Centroid distance signature is constructed from the segmented hand contours as a shape signature. Fourier transformation of the centroid distance signature results in fourier descriptors of the hand shape. The fourier descriptors of hand gesture are then compared with the gesture dictionary to perform gesture recognition. The performance of the gesture recognition using different distance metrics as classifiers is investigated. The test results show that the use of 15 Fourier descriptors and Manhattan distance-based classifier achieves the best recognition rates of 95% with small computation latency about 6.0573 ms. Recognition error is occurred due to the similarity of Fourier descriptors from some gesture. KeywordsGesture, Sign Language, Fingerspelling, CeFD, Fourier Descriptor.

A preliminary study to determine criteria for personalized e-commerce

Web design is one of several critical factors for the acceptance and success of an e-commerce website. A good web design influences users satisfaction and intention to use the website. The purpose of the study was to determine criteria for personalized e-commerce with a method recommended by users in using an e-commerce. This study used a qualitative method to analyze three components of web design i.e. information, navigation, and visual designs. Data collection was performed using in-depth interview technique on participants who have been familiar with online transactions. Data showed that participants preferred navigation and information designs rather than visual design.

Real time static hand gesture recognition system prototype for Indonesian sign language

Sign language uses gestures instead of speech sound to communicate. However, it is rare that the normal people try to learn the sign language for interacting with deaf people. Therefore, the need for a translation from sign language to written or oral language becomes important. In this paper, we propose a prototype system that can recognize the hand gesture sign language in real time. We use HSV (Hue Saturation Value) color space combined with skin detection to remove the complex background and create segmented images. Then a contour detection is applied to localize and save hand area. Further, we use SURF algorithm to detect and extract key point features and recognize each hand gesture sign alphabet by comparing with these user image database. Based on the experiments, the system is capable to recognize hand gesture sign and translate to Alphabets, with recognize rate 63 % in average.

Design of Automated Moving Stage with Adaptive Focus System to Support Microscopy Image Stitching

Image stitching is a method to obtain high-resolution images through compositing several image elements using invariant pattern recognizing and matching between each image elements involved. This method can remove resolution restriction in digital microscopy imaging. This study aims to design automated stitching with adaptive focus mechanism to achieve high-quality final stitched image. We attach three-axis microscopic actuator into Olympus CX-21 light microscope. The actuator has been programmed to support image elements capture with adaptive focus ability to compensate focus plane changes due to unevenness object surface, inhomogeneous slide thickness and imperfection of preparation holder. Testing results show automated moving stage has horizontal step resolution 0.198±0.001 μm/step with hysteresis 5.99±1.09 μm and vertical step resolution 0.197±0.004 μm/step with hysteresis 2.36±1.28 μm at maximum speed 3,675μm/sec in 16 sub-division microstep setting value. Automated moving stage has also linear response with R2=0.999. Adaptive focus testing show satisfied optimum objective height locking stability using identical factor ε=95% for every objective application below 100x. Adaptive focus success stabilizes Zopt for every image element to generate final stitched image with homogenous focus value.

Interoperability model for eGoverment service based on adaptive ontology

Nowadays, implementation of interoperability in eGoverment services become more important and larger,. As of reference, interoperability is connection of different systems, information and schema of working, in among different administrations which running together and could be applied around the world. Interoperability is implemented in eGoverment with various form that distinctive each other. Interoperability is very important in supporting eGoverment for achieving a good service. eGoverment applied interoperability schema to give a lot of service for the citizen and to achieve a one-stop government in a country. In addition, eGoverment services based interoperability is a part requirement for designing and implementing various eGovernment applications for certain goal. Today, Interoperability composed of heterogenity and dynamic data sources in a transaction. Therefore, in this paper we propose a novel approach to solve interoperability in eGoverment services with heterogeneous data source by using adaptive ontology schema.

Providing information sources domain for information seeking agent from organizing knowledge

This paper proposes a tracking mechanism to obtain the information sources that are stored on the personal knowledge organization which will be used to direct the search of information on the Internet by a software agent. Semantic representation of the organizer is viewed as a map of the information sources that are classified hierarchically based on the scopes of knowledge domains from the standpoint of the agent. The tracking mechanism by query will look for the information sources in the knowledge domains based on the same scope of a defined knowledge domain. This tracking will produce a list of information sources that will be followed to get the domain location as internet access preferences.

Leveraging Knowledge from Different Communities Using Ontologies

The purpose of this paper is to provide research based understanding of leveraging knowledge and managing knowledge within and across several communities using the poverty domain as a case study. We hypothesize that leveraging knowledge with a good taxonomy and a good integration process are good approaches to organize and share knowledge. Problems appear when a group of people in different communities share data and collaborate using different perceptions, different concepts, different terms (terminologies), and different semantics to represent the same reality. In this paper we present an approach to solve this problem. We will generate a common set of terms based on the terms of several different storage devices, used by different communities, in order to make data retrieval independent of the different perceptions and terminologies used by those communities. We use ontologies to represent the particular knowledge of each community and discuss the use of mapping and integration techniques to find correspondences between the concepts used in those ontologies.

Comparison expert and novice scan behavior for using e-learning

E-Learning is an important media that an educational institution must have. Successful information design for e-learning depends on its user’s characteristics. This study explores differences between novice and expert users’ eye movement data. This differences between expert and novice users were compared and identified based on gaze features. Each participant must do three main tasks of e-learning. This paper gives the result that there are differences between gaze features of experts and novices.