Search

Food inspection has been a serious matter in the food industry as the contamination by foreign materials such as metals, bone, plastics and glass in food plays a major impact on the industry. In spite of a great deal of effort to prevent mixing foreign bodies in food materials, food manufacturers have still not been able to detect them. Electrical Resistance Sensor to detect the foreign material in food detection sensor is constructed and presented in this work. This project focuses on how to design and implement the system to detect and distinguish between food and foreign material using resistance concept. The electrode plate of Electrical Resistance Sensor (ERS) is designed using COMSOL Multiphysics Software to see the electric field and contour of the electric potential of the system. The resistance value from the sensor is measured based on the AC Circuit concept. The alternating current from the sensor flows to the charge detector circuit providing the voltage corresponding to the resistance between the electrode pair. The voltage from the charge detector circuit has been amplified by the amplifier circuit to obtained DC output from an AC input signal. The voltage form circuit has been converted from the analog to digital signal using Bluetooth Electronics Application via Arduino Uno through HC-05 Bluetooth module. The Bluetooth Electronics Application is used as a graphical user interface (GUI) to display the condition of the material tested including food and foreign material to a smartphone.  The experiment results show that the electrical resistance sensor are able to detect the foreign material in food by changes of the resistance value. If the food was detected with the foreign material (non-conductive), the value of resistance will decrease due to the flow of electric current.

A vanishing point is where the perspective projections of a set of parallel lines converge in the image plane. Vanishing point estimation (VPE) is an essential task in many applications including image-based camera calibration, 3D reconstruction and road detection. In image-based road detection, the approaches that utilize vanishing point are proven to be more efficient and robust than other solutions. However, estimating vanishing point from a single road image has been a demanding task, due to the variant nature of road scene and the computation restraint of real time application. The common drawbacks of the current methods are the lack of robustness in different road scenes and the slow processing time. In this thesis, different VPE methods based on texture or edge features are investigated. This thesis proposes an efficient VPE method which is robust to different road scenes, and possesses fast processing time suitable for real-time applications. The proposed VPE method including three stages: extracting local texture orientation and edge maps, identifying the VP search space, and calculating VP scores with a voting scheme. Color tensor features are employed to extract texture orientation and edge maps. Based on these extracted map, the optimized search spaces for VP candidates and voters are identified using Hough transform and neighborhood pixels. The voting score function is defined with a novel weighting method and a simple Bayesian classifier to adaptively adjust the algorithm. Experiments and analysis of the VPE methods are performed with the Pedestrian Lane Vanish Point Estimation dataset, which is extended to more than 4000 images. The results shows that the proposed VPE method outperforms state-of-the- art methods in term of accuracy, robustness, and processing time.

A vanishing point is where the perspective projections of a set of parallel lines converge in the image plane. Vanishing point estimation (VPE) is an essential task in many applications including image-based camera calibration, 3D reconstruction and road detection. In image-based road detection, the approaches that utilize vanishing point are proven to be more efficient and robust than other solutions. However, estimating vanishing point from a single road image has been a demanding task, due to the variant nature of road scene and the computation restraint of real time application. The common drawbacks of the current methods are the lack of robustness in different road scenes and the slow processing time. In this thesis, different VPE methods based on texture or edge features are investigated. This thesis proposes an efficient VPE method which is robust to different road scenes, and possesses fast processing time suitable for real-time applications. The proposed VPE method including three stages: extracting local texture orientation and edge maps, identifying the VP search space, and calculating VP scores with a voting scheme. Color tensor features are employed to extract texture orientation and edge maps. Based on these extracted map, the optimized search spaces for VP candidates and voters are identified using Hough transform and neighborhood pixels. The voting score function is defined with a novel weighting method and a simple Bayesian classifier to adaptively adjust the algorithm. Experiments and analysis of the VPE methods are performed with the Pedestrian Lane Vanish Point Estimation dataset, which is extended to more than 4000 images. The results shows that the proposed VPE method outperforms state-of-the- art methods in term of accuracy, robustness, and processing time.

A vanishing point is where the perspective projections of a set of parallel lines converge in the image plane. Vanishing point estimation (VPE) is an essential task in many applications including image-based camera calibration, 3D reconstruction and road detection. In image-based road detection, the approaches that utilize vanishing point are proven to be more efficient and robust than other solutions. However, estimating vanishing point from a single road image has been a demanding task, due to the variant nature of road scene and the computation restraint of real time application. The common drawbacks of the current methods are the lack of robustness in different road scenes and the slow processing time. In this thesis, different VPE methods based on texture or edge features are investigated. This thesis proposes an efficient VPE method which is robust to different road scenes, and possesses fast processing time suitable for real-time applications. The proposed VPE method including three stages: extracting local texture orientation and edge maps, identifying the VP search space, and calculating VP scores with a voting scheme. Color tensor features are employed to extract texture orientation and edge maps. Based on these extracted map, the optimized search spaces for VP candidates and voters are identified using Hough transform and neighborhood pixels. The voting score function is defined with a novel weighting method and a simple Bayesian classifier to adaptively adjust the algorithm. Experiments and analysis of the VPE methods are performed with the Pedestrian Lane Vanish Point Estimation dataset, which is extended to more than 4000 images. The results shows that the proposed VPE method outperforms state-of-the- art methods in term of accuracy, robustness, and processing time.

A vanishing point is where the perspective projections of a set of parallel lines converge in the image plane. Vanishing point estimation (VPE) is an essential task in many applications including image-based camera calibration, 3D reconstruction and road detection. In image-based road detection, the approaches that utilize vanishing point are proven to be more efficient and robust than other solutions. However, estimating vanishing point from a single road image has been a demanding task, due to the variant nature of road scene and the computation restraint of real time application. The common drawbacks of the current methods are the lack of robustness in different road scenes and the slow processing time. In this thesis, different VPE methods based on texture or edge features are investigated. This thesis proposes an efficient VPE method which is robust to different road scenes, and possesses fast processing time suitable for real-time applications. The proposed VPE method including three stages: extracting local texture orientation and edge maps, identifying the VP search space, and calculating VP scores with a voting scheme. Color tensor features are employed to extract texture orientation and edge maps. Based on these extracted map, the optimized search spaces for VP candidates and voters are identified using Hough transform and neighborhood pixels. The voting score function is defined with a novel weighting method and a simple Bayesian classifier to adaptively adjust the algorithm. Experiments and analysis of the VPE methods are performed with the Pedestrian Lane Vanish Point Estimation dataset, which is extended to more than 4000 images. The results shows that the proposed VPE method outperforms state-of-the- art methods in term of accuracy, robustness, and processing time.

A vanishing point is where the perspective projections of a set of parallel lines converge in the image plane. Vanishing point estimation (VPE) is an essential task in many applications including image-based camera calibration, 3D reconstruction and road detection. In image-based road detection, the approaches that utilize vanishing point are proven to be more efficient and robust than other solutions. However, estimating vanishing point from a single road image has been a demanding task, due to the variant nature of road scene and the computation restraint of real time application. The common drawbacks of the current methods are the lack of robustness in different road scenes and the slow processing time. In this thesis, different VPE methods based on texture or edge features are investigated. This thesis proposes an efficient VPE method which is robust to different road scenes, and possesses fast processing time suitable for real-time applications. The proposed VPE method including three stages: extracting local texture orientation and edge maps, identifying the VP search space, and calculating VP scores with a voting scheme. Color tensor features are employed to extract texture orientation and edge maps. Based on these extracted map, the optimized search spaces for VP candidates and voters are identified using Hough transform and neighborhood pixels. The voting score function is defined with a novel weighting method and a simple Bayesian classifier to adaptively adjust the algorithm. Experiments and analysis of the VPE methods are performed with the Pedestrian Lane Vanish Point Estimation dataset, which is extended to more than 4000 images. The results shows that the proposed VPE method outperforms state-of-the- art methods in term of accuracy, robustness, and processing time.

A vanishing point is where the perspective projections of a set of parallel lines converge in the image plane. Vanishing point estimation (VPE) is an essential task in many applications including image-based camera calibration, 3D reconstruction and road detection. In image-based road detection, the approaches that utilize vanishing point are proven to be more efficient and robust than other solutions. However, estimating vanishing point from a single road image has been a demanding task, due to the variant nature of road scene and the computation restraint of real time application. The common drawbacks of the current methods are the lack of robustness in different road scenes and the slow processing time. In this thesis, different VPE methods based on texture or edge features are investigated. This thesis proposes an efficient VPE method which is robust to different road scenes, and possesses fast processing time suitable for real-time applications. The proposed VPE method including three stages: extracting local texture orientation and edge maps, identifying the VP search space, and calculating VP scores with a voting scheme. Color tensor features are employed to extract texture orientation and edge maps. Based on these extracted map, the optimized search spaces for VP candidates and voters are identified using Hough transform and neighborhood pixels. The voting score function is defined with a novel weighting method and a simple Bayesian classifier to adaptively adjust the algorithm. Experiments and analysis of the VPE methods are performed with the Pedestrian Lane Vanish Point Estimation dataset, which is extended to more than 4000 images. The results shows that the proposed VPE method outperforms state-of-the- art methods in term of accuracy, robustness, and processing time.

A vanishing point is where the perspective projections of a set of parallel lines converge in the image plane. Vanishing point estimation (VPE) is an essential task in many applications including image-based camera calibration, 3D reconstruction and road detection. In image-based road detection, the approaches that utilize vanishing point are proven to be more efficient and robust than other solutions. However, estimating vanishing point from a single road image has been a demanding task, due to the variant nature of road scene and the computation restraint of real time application. The common drawbacks of the current methods are the lack of robustness in different road scenes and the slow processing time. In this thesis, different VPE methods based on texture or edge features are investigated. This thesis proposes an efficient VPE method which is robust to different road scenes, and possesses fast processing time suitable for real-time applications. The proposed VPE method including three stages: extracting local texture orientation and edge maps, identifying the VP search space, and calculating VP scores with a voting scheme. Color tensor features are employed to extract texture orientation and edge maps. Based on these extracted map, the optimized search spaces for VP candidates and voters are identified using Hough transform and neighborhood pixels. The voting score function is defined with a novel weighting method and a simple Bayesian classifier to adaptively adjust the algorithm. Experiments and analysis of the VPE methods are performed with the Pedestrian Lane Vanish Point Estimation dataset, which is extended to more than 4000 images. The results shows that the proposed VPE method outperforms state-of-the- art methods in term of accuracy, robustness, and processing time.

A vanishing point is where the perspective projections of a set of parallel lines converge in the image plane. Vanishing point estimation (VPE) is an essential task in many applications including image-based camera calibration, 3D reconstruction and road detection. In image-based road detection, the approaches that utilize vanishing point are proven to be more efficient and robust than other solutions. However, estimating vanishing point from a single road image has been a demanding task, due to the variant nature of road scene and the computation restraint of real time application. The common drawbacks of the current methods are the lack of robustness in different road scenes and the slow processing time. In this thesis, different VPE methods based on texture or edge features are investigated. This thesis proposes an efficient VPE method which is robust to different road scenes, and possesses fast processing time suitable for real-time applications. The proposed VPE method including three stages: extracting local texture orientation and edge maps, identifying the VP search space, and calculating VP scores with a voting scheme. Color tensor features are employed to extract texture orientation and edge maps. Based on these extracted map, the optimized search spaces for VP candidates and voters are identified using Hough transform and neighborhood pixels. The voting score function is defined with a novel weighting method and a simple Bayesian classifier to adaptively adjust the algorithm. Experiments and analysis of the VPE methods are performed with the Pedestrian Lane Vanish Point Estimation dataset, which is extended to more than 4000 images. The results shows that the proposed VPE method outperforms state-of-the- art methods in term of accuracy, robustness, and processing time.