Joko Siswantoro

A linear model based on Kalman filter for improving neural network classification performance

This paper proposes a method to improve neural network classification performance.A linear model was used as post processing of neural network.The parameters of linear model was estimated using Kalman filter iteration.The method can be applied to classify an object regardless of the type of feature.The method has been validated with five different datasets. Neural network has been applied in several classification problems such as in medical diagnosis, handwriting recognition, and product inspection, with a good classification performance. The performance of a neural network is characterized by the neural networks structure, transfer function, and learning algorithm. However, a neural network classifier tends to be weak if it uses an inappropriate structure. The neural networks structure depends on the complexity of the relationship between the input and the output. There are no exact rules that can be used to determine the neural networks structure. Therefore, studies in improving neural network classification performance without changing the neural networks structure is a challenging issue. This paper proposes a method to improve neural network classification performance by constructing a linear model based on the Kalman filter as a post processing. The linear model transforms the predicted output of the neural network to a value close to the desired output by using the linear combination of the object features and the predicted output. This simple transformation will reduce the error of neural network and improve classification performance. The Kalman filter iteration is used to estimate the parameters of the linear model. Five datasets from various domains with various characteristics, such as attribute types, the number of attributes, the number of samples, and the number of classes, were used for empirical validation. The validation results show that the linear model based on the Kalman filter can improve the performance of the original neural network.

Monte Carlo Method with Heuristic Adjustment for Irregularly Shaped Food Product Volume Measurement

Volume measurement plays an important role in the production and processing of food products. Various methods have been proposed to measure the volume of food products with irregular shapes based on 3D reconstruction. However, 3D reconstruction comes with a high-priced computational cost. Furthermore, some of the volume measurement methods based on 3D reconstruction have a low accuracy. Another method for measuring volume of objects uses Monte Carlo method. Monte Carlo method performs volume measurements using random points. Monte Carlo method only requires information regarding whether random points fall inside or outside an object and does not require a 3D reconstruction. This paper proposes volume measurement using a computer vision system for irregularly shaped food products without 3D reconstruction based on Monte Carlo method with heuristic adjustment. Five images of food product were captured using five cameras and processed to produce binary images. Monte Carlo integration with heuristic adjustment was performed to measure the volume based on the information extracted from binary images. The experimental results show that the proposed method provided high accuracy and precision compared to the water displacement method. In addition, the proposed method is more accurate and faster than the space carving method.

Real World Coordinate from Image Coordinate Using Single Calibrated Camera Based on Analytic Geometry

The determination of real world coordinate from image coordinate has many applications in computer vision. This paper proposes the algorithm for determination of real world coordinate of a point on a plane from its image coordinate using single calibrated camera based on simple analytic geometry. Experiment has been done using the image of chessboard pattern taken from five different views. The experiment result shows that exact real world coordinate and its approximation lie on the same plane and there are no significant difference between exact real world coordinate and its approximation.

Natural Produce Classification Using Computer Vision Based on Statistical Color Features and Derivative of Radius Function

In agriculture industry, natural produce classification is used in sorting, grading, measuring, and pricing. Currently, a lot of methods have been developed using computer vision to replace human expert in natural produce classification. However, some of the method used long features descriptor and complex classifier to obtain high classification rate. This paper proposes natural produce classification method using computer vision based on simple statistical color features and derivative of radius function. The k-nearest neighbors (k-NN) and artificial neural network (ANN) were used to classify the produce based on the extracted features. Preliminary experiment results show that the proposed method achieved best result with average classification accuracy of 99.875% using ANN classifier with nine nodes in hidden layer.