Claim Missing Document
Check
Articles

Found 4 Documents
Search

Text Detection In Indonesian Identity Card Based On Maximally Stable Extremal Regions Angga Maulana Purba; Agus Harjoko; Mohammad Edi Wibowo
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 13, No 2 (2019): April
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.41259

Abstract

Most of Indonesian organizations either it is government or non government sometime required their member to provide their identity card (E-KTP) as legal document collection in their database. This collection of image usually being used as manual verification method. These document images acquired by each person with their own device, there are variations of angles they are used to acquire the image. This situation created problems in text recognition by OCR softwares especially in text detection part, orientation and noise will affect their accuracy. These cases making the text detection more complex and cannot be solved by simple vertical projection profile of black pixels.  This research proposed a method to improve text detection in identity document by fixing the orientation first, then using MSER regions to form text region. We fix the orientation using the line that made by Progressive Probabilistic Hough Transform. Then we used MSER to obtain all candidate regions and Horizontal RLSA acts as connector between those candidate. The orientation fixing strategy reach average of margin error 0.377o (in 360o system) and the text detection method reach 84.49% accuracy in best condition.
Deteksi Kantuk Pengemudi Berdasarkan Keterbukaan Mata Menggunakan Model Ringan dari Spatiotemporal Pyramidal CNN Angga Maulana Purba; Fajar Mahardika; Satriawan Desmana; Nur Moniroh
sudo Jurnal Teknik Informatika Vol. 4 No. 4 (2025): Edisi Desember
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/sudo.v4i4.1342

Abstract

Keselamatan berkendara merupakan hal yang penting dan menjadi topik yang krusial diperbincangkan termasuk mendeteksi kantuk pengemudi. Dalam Computer Vision salah satu pendekatan yang dilakukan adalah mendeteksi kedipan mata pengemudi. Penelitian tahun 2022 menunjukkan hasil yang baik dalam penggunaan Pyramidal Bottleneck CNN untuk mempelajari fitur spatio dan temporal pada kedipan mata. Kemudian tahun 2023 dikembangkan model yang lebih ringan dengan Depth-wise Separable Convolution, sehingga parameter latih bisa diperkecil. Oleh karena itu, Penelitian ini bertujuan mengadaptasi arsitektur tersebut untuk kasus keterbukaan mata. Kedipan mata berlangsung cukup singkat dan hanya sepersekian detik, sehingga belum cukup membantu untuk mendeteksi kantuk. Model tersebut berhasil dilatih pada data primer yang terbatas dan dibandingkan dengan model baseline. Model terbaik secara keseluruhan menghasilkan F1 score 0.75, Precision 0.63, dan Recall 0.93. Model tersebut bisa berjalan diatas CPU dengan rata-rata 12 FPS (Frame Per Second). Hasil recall yang cukup tinggi menunjukkan model tersebut bisa menangkap momen mata tertutup cukup banyak, hal ini cukup krusial karena kehilangan momen mata tertutup akan fatal akibatnya, meskipun harus mengorbankan precision atau masih tinggi false positive-nya.
Game Edukasi Bangun Datar Berbasis Android sebagai Media Pembelajaran Matematika di Sekolah Dasar: Studi Eksperimental Fadillah Istiqomah; Nur Muniroh; Angga Maulana Purba; Ratih Ratih
sudo Jurnal Teknik Informatika Vol. 4 No. 4 (2025): Edisi Desember
Publisher : Ilmu Bersama Center

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56211/sudo.v4i4.1355

Abstract

Pembelajaran matematika, khususnya materi bangun datar, sering dianggap sulit dan membosankan oleh siswa Sekolah Dasar (SD). Penelitian ini bertujuan untuk menguji efektivitas penggunaan game edukasi berbasis Android dalam meningkatkan pemahaman konsep bangun datar dan motivasi belajar siswa. Metode yang digunakan adalah studi eksperimen dengan desain pre-test dan post-test pada dua kelompok: kelompok eksperimen yang menggunakan game edukasi dan kelompok kontrol yang menggunakan metode pembelajaran konvensional. Sampel penelitian terdiri dari 40 siswa kelas IV SD yang dipilih secara purposive. Instrumen penelitian berupa tes pemahaman bangun datar dan kuesioner motivasi belajar. Hasil penelitian menunjukkan bahwa kelompok eksperimen mengalami peningkatan signifikan pada skor pemahaman bangun datar dibandingkan kelompok kontrol (rata-rata post-test kelompok eksperimen: 85,2; kelompok kontrol: 72,4). Berdasarkan kuesioner motivasi belajar, 90% siswa kelompok eksperimen menyatakan merasa lebih tertarik dan termotivasi belajar matematika menggunakan game edukasi, dibandingkan 55% pada kelompok kontrol. Temuan ini menunjukkan bahwa integrasi teknologi mobile dalam pembelajaran matematika dapat menjadi strategi efektif untuk meningkatkan pemahaman konsep dan minat belajar siswa SD.
Deep Learning-Based Classification of Cikadu Batik Motifs Using ResNet50 and MobileNetV2 Rizki Ripai; Fajar Mahardika; Fazar Sidik; Nurul Badriah; Angga Maulana Purba
Sinkron : jurnal dan penelitian teknik informatika Vol. 10 No. 3 (2026): Article Research July 2026
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v10i3.16368

Abstract

Batik motif recognition is essential for cultural heritage preservation and the digitization of traditional Indonesian textile knowledge. This study proposes a deep learning-based framework for the automatic classification of Cikadu Batik motifs from Tanjung Lesung, Banten — a regionally distinct batik pattern that has not been systematically studied in prior computational literature. Two convolutional neural network (CNN) architectures were implemented and comparatively evaluated under identical experimental conditions: ResNet50, a high-capacity model employing residual skip connections, and MobileNetV2, a lightweight model utilizing depthwise separable convolutions and inverted residual blocks. A curated dataset of 2,500 images spanning five motif classes was constructed through collaboration with local batik artisans, preprocessed via resizing (224×224), pixel normalization, and augmentation (rotation, zoom, horizontal flip, brightness adjustment), and partitioned using a stratified 70:15:15 split. Both models were trained with transfer learning from ImageNet weights, using the Adam optimizer (lr=0.0001), categorical cross-entropy loss, batch size of 32, and early stopping over 30 epochs. Model evaluation employed accuracy, precision, recall, F1-score, AUC-ROC, inference time, and parameter count. ResNet50 achieved 95.51% accuracy, 95.67% precision, 95.34% recall, 95.50% F1-score, and 99.56% AUC-ROC, with an inference time of 18.2 ms and 25.64 million parameters. MobileNetV2 achieved 92.13% accuracy, 92.28% precision, 91.98% recall, 92.13% F1-score, and 98.89% AUC-ROC, with an inference time of 8.7 ms and only 3.54 million parameters — approximately 7× lighter and 2× faster. These results empirically establish a clear accuracy-efficiency trade-off, with ResNet50 favored for accuracy-critical server-based systems and MobileNetV2 better suited for real-time mobile deployment. This study constitutes the first published benchmark for deep learning-based Cikadu Batik classification and provides a principled basis for architecture selection in regional batik recognition applications