IDENTIFICATION OF INCOMPLETE PENETRATION WELDING DEFECTS ON DIGITAL RADIOGRAPHIC FILM FIGURES WITH THE GEOMETRIC INVARIANT MOMENT

The examination of defects in radiographic films necessitates specialized knowledge, as indicated by an expert radiographer (AR) degree, yet the subjectivity of AR in identifying defects is problematic. To overcome this subjectivity, an automatic welding defect identification is needed. This is executed by using Matlab to create artificial neural networks, which is beneficial for users with the graphical user interface (GUI) feature. One of the breakthroughs in the figure extraction into seven feature vector values is the geometric invariant moment theory. This prevents translation, rotation, and scaling from changing the figure's characteristics. Therefore, a welding defect identification system with a geometric invariant moment was created in the digital radiographic film figure to overcome the reading error by AR. The identification system obtained an accuracy rating of 89.9%.

Klasifikasi Jenis dan Tingkat Kesegaran Daging Berdasarkan Warna, Tekstur dan Invariant Moment Menggunakan Klasifikasi LDA

Distribution process that takes a long time along with improper treatment, can cause meat become not fresh and decrease the quality of the meat. Therefore, unscrupulous meat sellers cheating on the non-fresh meat by mixing the non-fresh meat with the fresh one. A system that can classify the type and freshness level of meat automatically is needed. In this research, that system was developed based on texture, color and shape features using Linear Discriminant Analysis (LDA) classification. The methods used in the feature extraction process are statistical approach, GLCM and the HU's invariant moment. The total of data used in this research was 960 images of 3 different meat types which are chicken meat, goat meat, and beef. The highest accuracy obtained from the testing process was 90% on the combination features of HSI and invariant moment for the meat type in refrigerator

Multi-Spectral Hybrid Invariant Moments Fusion Technique for Face Identification

For reliable face identification, the fusion process of multi-spectral vision features produces robust classification systems, this paper exploits the power of thermal facial image invariant moments features fused with the visible facial image invariant moments features to propose a new multi-spectral hybrid invariant moment fusion system for face identification. And employs Feed-forward neural network to train the moments' features and make decisions. The evaluation system uses databases of visible thermal pairs face images CARL and UTK-IRIS databases and gives an accuracy reaches 99%.

Klasifikasi Kain Songket Lombok Berdasarkan Fitur GLCM dan Moment Invariant Dengan Teknik Pengklasifikasian Linear Discriminant Analysis (LDA)

Songket is one of Indonesia's cultural heritage that is still present today. One of the most famous songket woven fabrics is the Lombok songket. Lombok songket has diverse, unique, and beautiful motifs. However public knowledge of Lombok songket motifs is still minimal and the difference between one motif with another is still unknown. The lack of digitalized data collection is one reason for this. Therefore, we need a system that can classify the Lombok songket automatically. In this study, a system was developed based on texture features and shape features using Linear Discriminant Analysis (LDA). The GLCM method is used in the texture feature extraction process and the Invariant Moment method is used in the feature extraction process. The total data used in this study is 1000 images from 10 Lombok songket motifs which are divided into training data and test data. The highest accuracy is obtained on the Invariant Moment and GLCM feature with an image resolution of 300x300 pixels using the most effective feature that is equal to 96.67%.

IMPLEMENTATION OF MOMENT INVARIANT IN RECOGNIZING OF ELECTRICAL METER NUMBERS

Implementation of computer vision can be done in the introduction of images or pictures of characters of numbers or letters. Based on this, then the computer vision can be used in the introduction of numbers on the electric meter or commonly called kWh meter. The underlying thing for the electric meter to be the object of research is to look at the situation, where the electric meter recorder keeps the record using the camera. Furthermore, the value shown on the electric meter will be inputted manually. Manual input requires a relatively long time because the amount of electricity meter input value is not small data. One method that can be used in recognizing the shape of the image in computer vision is the invariant moment. The results of this study indicate that the quality of the image gives effect, both in terms of the extraction of features and the accuracy of the recognition of the figure on the image of the electric meter. In addition to this, the threshold value of the euclidian distance method should also be used to limit the recognition process.

Sistem Temu Kembali Citra Menggunakan Ciri Multi Tekston Histogram dan Invariant Moment

Image retrieval is an image search method by performing a comparison between the query image and the image contained in the database based on the existing information. This study proposes to save the characteristic of Indonesian batik, so the system can help in the prevention of claims from other countries. This study discusses the content-based image retrieval using Multi Texton Histogram and Invariant Moment. MTH is known as a method of describing the characteristics of the surface texture, and IM is a method that produces characteristic geometry of an object and the introduction of geometry that are independent of translation, rotation, and scaling. This study used 10,000 each Batik and Corel images as datasets. The system will take random sample of 7,000 images as training data and the rest is used as the testing data. As the result, Batik Dataset produces precision of 99.75% and a recall of 14:25%. While Corel Dataset produces precision of 36.63% and a recall of 5:23%. The system generates a better performance in the Batik dataset because batik texture is monotonous. While, the Corel dataset has more diversified of the shape and texture. Keywords: Batik, Image Retrieval, multi texton histogram, invariant moment