Brail is a written mode of communication utilized by individuals with visual impairments to engage in interpersonal exchanges. The braille writing system consists of patterns printed on specialized paper that feature embossed dots. Braille documents enable the visually impaired to acquire knowledge and information exclusively through the application of their sense of contact. Comprehending braille is not a simple undertaking, particularly for the general populace. Because braille is not a required subject in Indonesian education, the majority of the population lacks proficiency in the language. This may therefore result in a minor communication barrier between visually impaired individuals and non-impaired individuals. In order to address this challenge, the present study employs digital image processing via the deep convolutional neural network (DCNN) technique to facilitate comprehension of braille document contents by non-braille speakers. This study employs a deep learning technique that is highly accurate, effective at image processing, and capable of recognizing complex patterns. This study employed the following image processing methods: grayscaling, filtering, contrast enhancement, thresholding, morphological operation, and resizing. Following testing in this investigation, it was determined that the proposed method accurately identifies embossed braille images with a precision of 99.63%.

This study aims to optimize the object identification process, especially identifying trash in the house compound. Most object identification methods cannot distinguish whether the object is a real image (3D) or a photographic image on paper (2D). This is a problem if the detected object is moved from one place to another. If the object is 2D, the robot gripper only clamps empty objects. In this study, the Sequential_Camera_LiDAR (SCL) method is proposed. This method combines a Convolutional Neural Network (CNN) with LiDAR (Light Detection and Ranging), with an accuracy of ±2 mm. After testing 11 types of trash on four CNN architectures (AlexNet, VGG16, GoogleNet, and ResNet18), the accuracy results are 80.5%, 95.6%, 98.3%, and 97.5%. This result is perfect for object identification. However, it needs to be optimized using a LiDAR sensor to determine the object in 3D or 2D. Trash will be ignored if the fast scanning process with the LiDAR sensor detects non-real (2D) trash. If Real (3D), the trash object will be scanned in detail to determine the robot gripper position in lifting the trash object. The time efficiency generated by fast scanning is between 13.33% to 59.26% depending on the object’s size. The larger the object, the greater the time efficiency. In conclusion, optimization using the combination of a CNN and a LiDAR sensor can identify trash objects correctly and determine whether the object is real (3D) or not (2D), so a decision may be made to move the trash object from the detection location.