Geez Numbers

Researches have been done on Ethiopic scripts. However studies excluded the Geez numbers from the studies because of different reasons. This paper presents offline handwritten and machine printed Geez number recognition using feed forward back propagation artificial neural network. On this study, different Geez image characters were collected from google image search and three persons are instructed to write the numbers using pencil. In total we have collected 560 numbers of characters. We have used 460 of the characters for training and 100 are used for testing. Accordingly we have achieved overall all classification ~89:88%

We also use the apostrophe for Ethiopic numbers, so '1 becomes and so on. If an English apostrophe ' is needed in your document, type it twice: ''. This works for other punctuation as well,so typing ; once makes and a second time gives English semi-colon ;.

Geez Numbers

Download 🔥 https://shurll.com/2y4COI 🔥

Got the idea for this series when I wanted to learn the new Blender feature that is geometry nodes. Combining different shapes such as cubes, cylinders, cones, hexagon and spheres to be instanced on traditional Geez numbers gave me these results. These became more visually pleasing when combined with monochromatic color palettes.

Handwritten character and digit recognition works are done in different languages to improve the efficiency of the recognition when they digitize historical and handwritten documents [4]. Digit recognition is a well-known problem that has been used to document indexing using dates such as document date, birth date, marriage date, and death date [5]. Digit recognition and detection have been utilized in a variety of applications, including automated the reading of the number of bank cheques, postal numbers and codes, tax forms, and document indexing based on dates [6]. There are two types of architectures for handwritten digit string recognition. The two strategies for recognizing the digit string are detection-free and segmentation-based recognition [7]. In segmentation based on the system, we first detect the numerical string that may contain multiple digits. Splitting digits should be done before a recognition to isolate each digit [8, 9]. However, detection-free recognition approach recognizes each digit without any splitting and detection preprocesses [10].

Most of the researchers did digit recognition on English numbers. They achieved high performance using different methods to recognize handwritten digits. For English handwritten digits, there are many resources and datasets ready to be used by the research community. It encourages the researchers to focus on that area. However, for Geez handwritten digits, there are no organized data in public for researchers to work on recognition of handwritten digits. Some researchers did Geez character recognition for machine-printed and handwritten characters but they did not focus on digits, especially for handwritten. The author of [3] is the first researcher to work on recognizing handwritten Geez digits, but the dataset he used was a very small and low performance made.

For this study, handwritten data were collected from a variety of people with various writing styles. Instead of manual feature extraction, which is difficult for humans to do, deep learning models are utilized, which are life-simplifying and efficient techniques to extract with high accuracy, and performance. A data-gathering paper was created for this purpose. The data gathering paper is prepared in a way to make the pre-processing easier. The paper is A4 size which consists of the symbol of all 20 Geez numbers, in 2 rows and 10 columns in a box, and other same-sized empty boxes prepared and repeated 5 times as shown in Figure 2. This means an individual has to handwrite 100 instances or digits. The data were collected from 524 different individuals and each person gave 100 instances of digits. According to calculations, since the collected data are from 524 different individuals, 52,400 instances are obtained. People from many demographic groups participated in the data collection. The data were gathered from elementary pupils, high school students, high school staff members, university students, and university academic staff (lecturers). The majority of information was acquired from university students, which totaled roughly to 250 at Adama Science and Technology University.

Table 3 describes the CNN configuration and parameters for the six cases. The models have varies numbers of convolutional and fully connected layers, as well as different layer organizations. The first fully connected layer contains 128 neurons and the second contains 20 neurons in all cases.

These numbers all descend from Proto-Semitic, as Amharic is a Semitic language. They are all cognates of (related to) Arabic numbers, which makes sense, as Arabic is also a Semitic language. In fact, after Arabic, Amharic is the second most spoken Semitic language in the world! e24fc04721