Machine recognition of hand-drawn circuit diagrams

Edwards, Brett; Chandran, Vinod

doi:10.1109/icassp.2000.860185

Cited by 22 publications

(14 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whereas in [3] online hand drawn circuit diagram connected components and connector are segmented using a continuous time varying stroke stream in different eight directions using HMM and classification is performed using viterbi algorithm. [4] Address the problem of recognizing the circuits from the scanned image. In this method, image is pre-processed and components are segmented using spatial pixel density by manually choosing appropriate threshold.…”

Section: Related Workmentioning

confidence: 99%

“…The method has been tested on 9 components, the node are classified using syntactic analysis. However, the methods [3] and [4] do not handle the scale and orientation changes in the images. To address the problem of similarity transformation, [5] the method which works for online hand drawn circuit is recognized with scale, translation and rotation invariant recognition.…”

Section: Related Workmentioning

confidence: 99%

“…The circuit line thickness is adjusted to single pixel level using some morphological operation. [4] The line and components have a different pixel density over a K×K neighbourhood region the pixel density of component is usually higher than that of the line segment over the same region (K×K). The pixel density is estimated over a K×K neighborhood region.…”

Section: Ircuit Recognitionmentioning

confidence: 99%

See 2 more Smart Citations

Handwritten Electric Circuit Diagram Recognition: An Approach Based on Finite State Machine

R¹,

Dinesh²,

Prabhanjan³

2019

IJMLC

View full text Add to dashboard Cite

In this paper we propose a method for recognizing hand drawn electronic circuit diagrams. The proposed method first detect and classify each components present in the hand drawn circuit diagram. For the purpose of component recognition, we have constructed the feature vector by combining Local Binary Pattern (LBP) and statistical features based on pixel density. Classification of components is done by using support vector machine (SVM) classifier. Upon detection and recognition of components, the proposed method subsequently uses the position and sequence of arrangement of components to determine the type of circuit. For the purpose of establishing the sequence of components we have used finite state machine. The proposed method represents the sequence of recognized components as a string. This string representation of circuit is fed to a Finite State Machine (FSM) to detect type of circuit. The proposed method has been tested on about 100 hand written circuit diagrams of varying complexities and of different types. The proposed component detection method gives over 99% accuracy whereas, the circuit recognition method has recognition rate of over 85% recognition rate for the circuit type recognition.Index Terms-Circuit recognition, finite state machine, Local binary pattern, SVM, statistical features.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Ircuit Recognitionmentioning

confidence: 99%

See 1 more Smart Citation

Handwritten Electric Circuit Diagram Recognition: An Approach Based on Finite State Machine

R¹,

Dinesh²,

Prabhanjan³

2019

IJMLC

View full text Add to dashboard Cite

show abstract

“…In another study [7], a system for recognition of hand-drawn circuit diagrams is presented. Scanned images of circuit diagrams are first preprocessed and binarized.…”

Section: Related Workmentioning

confidence: 99%

Segmentation and Recognition of Electronic Components in Hand-Drawn Circuit Diagrams

Moetesum¹,

Younus²,

Warsi³

et al. 2018

ICST Transactions on Scalable Information Systems

View full text Add to dashboard Cite

This paper presents an effective technique for segmentation and recognition of electronic components from hand-drawn circuit diagrams. Segmentation is carried out by using a series of morphological operations on the binarized images of circuits and discriminating between three categories of components (closed shape, components with connected lines, disconnected components). Each segmented component is characterized by computing the Histogram of Oriented Gradients (HOG) descriptor while classification is carried out using Support Vector Machine (SVM). The system is evaluated on 100 hand-drawn circuit diagrams with a total of 350 components. A segmentation accuracy of 87.7% while a classification rate of 92% is realized demonstrating the effectiveness of the proposed technique.

show abstract

“…Donald Bailey, Andrew Norman and Giovanni Moretti recognized printed circuits based on chain codes .The chains formed by the chain codes which are representation of the segments of the component symbols and interconnecting lines are used to recognize the components based on graphical primitives and regrouping them by predefined component definitions [10]. B.Edwards and V.Chandran used a nearest neighbor classifier which uses 35 features from each component, consisting of geometrical features, polygonal approximations and Hu invariant moments along with other features [11]. Most of the research related to offline circuit recognition involves identifying a set of patterns for the components and to create a grammar or a set of definitions for the components.…”

Section: Related Workmentioning

confidence: 99%

Circuit recognition using netlist

Sridar¹,

Subramanian²

2013

2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013)

View full text Add to dashboard Cite

The existing software for circuit design and simulation require the user to be skilled either with good programming ability or 'pick and paste' model. To remove this barrier of programming knowledge, we propose a simulation model where a circuit drawn on a paper will be simulated. The circuit drawn on the paper will be fed to the computer using a scanner/camera. The image is de-noised and the nodes in the circuit are detected. All the characters, numbers and symbols alone are stored in a separate image which is used for optical character recognition. After node detection and character recognition, a netlist is compiled which is used for simulation. Applications of this simulation model include smart teaching systems, tablet app and with more research, a great deal of components including transistors and ICs can be simulated.

show abstract

Machine recognition of hand-drawn circuit diagrams

Cited by 22 publications

References 4 publications

Handwritten Electric Circuit Diagram Recognition: An Approach Based on Finite State Machine

Handwritten Electric Circuit Diagram Recognition: An Approach Based on Finite State Machine

Segmentation and Recognition of Electronic Components in Hand-Drawn Circuit Diagrams

Circuit recognition using netlist

Contact Info

Product

Resources

About