by Christian Pratama (Faculty of Biotechnology, Atma Jaya Catholic University of Indonesia)
2. Automatic Status Identification of Microscopic Images Obtained from malaria Thin Blood Smears
by Dian Anggraini ( Faculty of Life Science, Department of Biomedical Engineering, Swiss German University)
Development of an accurate laboratory diagnostic tool, as recommended by WHO, is the key step to overcome the serious global health burden caused by malaria. This study aims to explore the possibility of computerized diagnosis of malaria and to develop a novel image processing algorithm to reliably detect the presence of malaria parasite from Plasmodium falciparum species in thin smears of Giemsa stained peripheral blood sample. The algorithm was designed as an expert system based on the method used by medical practitioner performing microscopy diagnosis of malaria. Digital images were acquired using a digital camera connected to a light microscope. Prior to processing, the images were subjected to gray-scale conversion to decrease image variability. Global thresholding was implemented to obtain erythrocyte and other blood cell components in each image. The segmented images were further processed to obtain informative features that were further used in classification stage. Two-stage classification using selected features was built based on Bayesian Decision Theory. Malaria samples prepared and provided by Eijkman Institute of Molecular Biology Indonesia were used to build and test the proposed algorithm.
Keywords: malaria, thin blood smears, image segmentation, thresholding
Publication related to no.1 and 2:
Automatic Status Identification of Microscopic Images Obtained from Malaria Thin Blood Smears, Dian Anggraini, Anto Satriyo Nugroho, Christian Pratama, Ismail Ekoprayitno, Aulia Arif Iskandar, Reggio Nurtanio Hartono, to appear in Proc. 3rd International Conference on Electrical Engineering and Informatics (ICEEI 2011), Institut Teknologi Bandung, Bandung, Indonesia, July 17-19, 2011
3. Development of Indonesian Automated Document Reader: Evaluation of Text Segmentation Algorithms
by Teresa Vania Tjahja (Faculty of Information Technology, Swiss German University)
In developing countries such as Indonesia, textual information is carried mostly bypaper medium. Such information, however, is not available to citizens with visualimpairment. To assist them, Agency for the Assessment and Application ofTechnology (Badan Pengkajian dan Penerapan Teknologi; BPPT) develops Indonesian Automated Document Reader (I-ADR), which converts textualinformation on paper documents to speech. This research is conducted to develop aprototype of I-ADR featuring OCR, Text Summarization, and Text-to-Speech (TTS)Synthesizer modules. The main focus is Text Segmentation module as an integral partof OCR. In this study, several Text Segmentation algorithms for grayscale and colorimages are developed and evaluated, with priority over algorithms for grayscaleimages. Text segmentation for grayscale images uses an improved version ofEnhanced CRLA (Sun, 2006), while segmentation for color images employsmultivalued image decomposition algorithm (Jain and Yu, 1998) combined with theimproved Enhanced CRLA. Based on the experiments, the success rate for grayscaleimages is 100% and 96.35% for color images
Keywords – visual impairment, text segmentation, text summarization, text-to-speechsynthesizer, OCR.
Recursive Text Segmentation for Indonesian Automated Document Reader for People with Visual Impairment, Teresa Vania Tjahja, Anto Satriyo Nugroho, James Purnama, Nur Aziza Azis, Rose Maulidiyatul Hikmah, Oskar Riandi, Bowo Prasetyo, to appear in Proc. 3rd International Conference on Electrical Engineering and Informatics (ICEEI 2011), Institut Teknologi Bandung, Bandung, Indonesia, July 17-19, 2011
4. Approximation Model for Fingerprint Orientation Field Correction
by Andree Ang Kisjanto Surya (Faculty of Information Technology, Swiss German University)
The estimation of fingerprint Orientation Field (OF) plays an important role in most fingerprint feature extraction algorithms. Many of the later stages in fingerprint feature extraction process (e.g. ridge enhancement, singular points detection) utilize fingerprint OF information as a cornerstone, thus the far-reaching implication of its estimation to the whole recognition process. Unfortunately, the accurate and robust estimation of fingerprint OF in low-quality fingerprint images is difficult and still remains as a challenge until today. This research attempts to evaluate the effectiveness of the fingerprint OF correction approaches based on the use of an approximation model derived from regression analysis. From the experimental results, it can be seen that performance of the approximation model based on Fourier basis is comparable to the classical filter-based approach to refine fingerprint OF. For practical purpose, a minor workaround can be utilized to significantly enhance the performance of a Fourier series model. For the advancement of research on related fields, the author recommends a further exploration to search for a mathematical model which can better extrapolate fingerprint’s ridge structure.
Keywords: Fingerprint, Orientation Field, approximation model, regression analysis