Vol.:(0123456789) SN Computer Science (2022) 3:87 https://doi.org/10.1007/s42979-021-00935-8 SN Computer Science ORIGINAL RESEARCH Image Abstraction Framework as a Pre‑processing Technique for Accurate Classifcation of Archaeological Monuments Using Machine Learning Approaches M. P. Pavan Kumar 1  · B. Poornima 2  · H. S. Nagendraswamy 3  · C. Manjunath 4  · B. E. Rangaswamy 5  · M. Varsha 2  · H. P. Vinutha 2 Received: 8 June 2021 / Accepted: 10 October 2021 / Published online: 26 November 2021 © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2021, corrected publication 2022 Abstract This work extricates the image characteristic features for the classifcation of archeological monument images. At the pre- processing stage, archeological dataset sample images are treated by using structure safeguarding image abstraction frame- work, which can deliver the most efective image abstraction output by manipulating the perceptible features in the given low-illuminated and underexposed color image samples. Proposed abstraction-framework efectively boosted the signifcant image property features like color, edge, sharpness, contrast and suppresses complexity and noise. The image properties were also refned at each phase based on the attained statistical feature disposal information. The work adopted the Harris feature identifcation technique to identify the most signifcant image features in the input and enhanced images. The framework also preserves signifcant features in the foreground of an image by intelligently integrating the series of flters during rigor- ous experimental work and also diminishes the background content of an input image. The proposed archeological system evaluates every stage of the result with assorted subjective matters and calculates the image quality and properties assess- ment statistical attributes. By this way prominent features in an image have been recognized. The efciency of this work has been corroborated by performing the trials on the selected archeological dataset. In addition, user’s visual feedback and the standard image quality assessment techniques were also used to evaluate the proposed pre-processing framework. Based on the obtained abstraction images from the framework, this work extracts the image gray color texture features using GLCM, color texture from CTMs and deep-learning features from AlexNet for the classifcation of archeological monument clas- sifcation. This work adopted a support vector machine as a classifer. To corroborate the efciency of the proposed method, an experiment was conducted on our own data set of Chalukya, Kadamba, Hoysala and new engraving monuments, each domain consisting of 500 archeological data set samples with large intra-class variation, with diferent environmental light- ing condition, low-illumination and diferent pose. Implementation of this work was carried out in MATLAB-2020 with HPC Nvidia Tesla P100 GPU, and obtained results show that combination of multiple features signifcantly improves the performance to the extent of 98.10%. Keywords Non-photorealistic rendering (NPR) · Image abstraction · Denoising convolutional neural network (DnCNN) · Weighted gradient sticks fltering (WGSF) · Anisotropic difusion-Kuwahara fltering (ADKF) · Gray-level co-occurrence matrix (GLCM) · Color texture moments (CTMs) Introduction History is the record of the past and is very important viewed from a scientifc and social standpoint. Source of informa- tion for the study is in the form of literature and archeol- ogy. Written sources are further classifed into indigenous and foreign writing. Archaeology sources mainly consist of excavation (vertical and horizontal); archaeology extracts information on past human civilization by excavation, * M. P. Pavan Kumar pavankumarjnnce@gmail.com; pavankumarmp@jnnce.ac.in; joiscmanjunath@gmail.com Extended author information available on the last page of the article Content courtesy of Springer Nature, terms of use apply. Rights reserved.