Use of Automatic Chinese Character Decomposition and Human Gestures for Chinese Calligraphy Robots

Abstract

Conventional Chinese calligraphy robots often suffer from the limited sizes of predefined font databases, which prevent the robots from writing new characters. This paper presents a robotic handwriting system to address such limitations, which extracts Chinese characters from textbooks and uses a robot's manipulator to write the characters in a different style. The key technologies of the proposed approach include the following:(1) automatically decomposing Chinese characters into strokes using Harris corner detection technology and (2) matching the decomposed strokes to robotic writing trajectories learned from human gestures. Briefly, the system first decomposes a given Chinese character into a set of strokes and obtains the stroke trajectory writing ability by following the gestures performed by a human demonstrator. Then, it applies a stroke classification method that recognizes the decomposed strokes as robotic writing trajectories. Finally, the robot arm is driven to follow the trajectories and thus write the Chinese character. Seven common Chinese characters have been used in an experiment for system validation and evaluation. The experimental results demonstrate the power of the proposed system, given that the robot successfully wrote all the testing characters in the given Chinese calligraphic style.

GANCCRobot: Generative adversarial nets based chinese calligraphy robot

“…The calligraphy robot system has two functions: (1) writing a stroke using the stroke trajectory points; (2) converting the stroke to an image. The training objectives of the model are summarized as follows: (1) to train the discriminative module to minimize the classification error rate, (2) to train the auxiliary distribution module to maximize the mutual information between the specified latent codes c, and the output of the generative module; (3) to train the generative module to generate the stroke trajectory points such that the trajectory is difficult for the discriminative module to classify and has the implicit features expressed in the latent codes c.…”

“…Robotics has been widely applied to promote human culture and education, such as robotic Chinese character writing [1,2], dancing, and drawing. Robotic writing is a particularly hot topic due to the great applicability of its key technology in other applications, including robotic drawing [3], industrial welding [4,5], and medical rehabilitation [6] among others.…”

Deep Learning-Based Hypothesis Generation Model and Its Application on Virtual Chinese Calligraphy-Writing Robot

“…To validate the feasibility of the proposed hypothesis generation model, we show a virtual robot with its cognition system can learn how to write Chinese calligraphy in a simulation environment through thinking and practicing from a human writing sample. Chinese calligraphy writing, which is regarded a difficult task requiring extremely complicated motions [22]- [25], focuses on changing the speed, press, strength, orientation, and angle [26] of a writing brush to write aesthetic calligraphy. It is complicated for designers to analyze the strokes of characters in different styles.…”

Integration of an actor-critic model and generative adversarial networks for a Chinese calligraphy robot

“…To achieve this task, the model must have many abilities, such as perceiving environmental information [2], planning and executing complex actions [3], and evaluating writing results [4]. To implement these capabilities, many technologies, such as robot motion planning [5], human-computer interaction [6,7], and evaluation method construction [8], are required. In particular, these abilities are fundamental technologies for autonomous robots in industrial and daily-life applications.…”