Digit Recognition Using Local Projection Dependent Clustering

Water companies utilize water meters to measure and calculate usage bills. However, the current process employed by PDAM requires redundant resources, as it involves taking photos of each customer's house having other officers read numbers from meter images, resulting in inefficiency. The problem is further compounded neglect improper maintenance meters, with some being buried garbage or soil. Additionally, contribute challenges capturing blurry tilted photos, hindering accurate reading numbers. This study applies a system processing converting them into text using image methods images Neural Networks perform digit recognition. includes steps such (1) grayscale conversion, (2) gamma correction, (3) x-Histogram Projection, (4) White Temporal Ascent Accumulation, (5) Peak Identification. Furthermore, segmentation techniques are applied enhance quality eliminate noise clustering methods. segmented then processed neural network recognize digits. achieves recognition accuracy 75.2%, despite encountering various technical non-technical during photo capture process.