scholarly journals Generating Masks for Image Segmentation in Digitized Herbarium Specimens

2019 ◽  
Vol 3 ◽  
Author(s):  
Alexander White ◽  
Rebecca Dikow ◽  
Makinnon Baugh ◽  
Abby Jenkins ◽  
Paul Frandsen
Keyword(s):  
Image Segmentation ◽  
Background Noise ◽  
Plant Material ◽  
Training Data ◽  
Herbarium Specimens ◽  
Complex Information ◽  
Museum Data ◽  
Specimen Material ◽  
Herbarium Sheet ◽  
Pattern Shape

Digitized herbarium images contain complex information unrelated to the shape and color of the specimens represented within them. This information can contribute a substantial amount of noise if one is to use the image as a proxy for pattern, shape, or color of the specimen. Image segmentation, whereby the specimen material is partitioned from the background (e.g., herbarium sheet, label, color ramp), offers one possible solution, yet training data for image segmentation of herbarium specimens is nonexistent. We present a pipeline for generating training data for image segmentation tasks along with a novel dataset of highly resolved image masks segmenting plant material from background noise. This dataset can be used to train neural networks to segment plant material in herbarium sheets more generally, and our method is applicable to other museum data sources where masking may be useful for quantitative analysis of patterns and shapes

scholarly journals Engaging Children with Herbarium Specimens at Royal Botanic Gardens Kew’s Science Festival

2018 ◽  
Vol 2 ◽  
pp. e25933
Author(s):  
Melissa Bavington
Keyword(s):  
Plant Material ◽  
Scientific Data ◽  
Lessons Learned ◽  
Specimen Preparation ◽  
Herbarium Specimens ◽  
Full Time ◽  
Plant Parts ◽  
Herbarium Collection ◽  
Herbarium Sheet ◽  
Royal Botanic Gardens

The Kew and Wakehurst Science Festivals consists of five days of activities over two weekends. Workshops and tours allow visitors to engage with the scientists and their research. We designed an interactive experience, so children could understand what a herbarium sheet is and the process of making one. The Herbarium accessions an average of 30,000 specimens per year and because specimens need to have a long life and be able to withstand being handled for hundreds of years they need to be ‘mounted’ according to strict protocols and guidelines. Botanical specimens are vital to research at Kew and beyond, providing key scientific data. Once mounted onto herbarium sheets botanical specimens are added to the Herbarium and made widely available to visiting scientists and researchers. Digitising these specimens increases access further through online portals. To achieve a specimen that can be handled for many years the specimens are mounted onto archival paper, along with their labels, before being added to the collection. There are 6 members in RBG Kew’s Specimen Preparation team who work full time to prepare botanical specimens for accession into the Herbarium collection; which currently stands at 7 million specimens and the oldest dates from the 1700s. We simplified this specimen preparation process down to the basic component parts of paper, glue, plant material and pressing. Using material and tools that visitors would be able to find for themselves; art paper, child friendly glue and plant material used in flower crafts we created a hands-on experience for mounting a herbarium specimen. The Science Festival is now in its 3rd year and each year the activity has been modified based on lessons learned over the course of the festival and each year. The stall is immensely popular going from 300 participants in the first year to over 700 in 2017. In the second year we added a new dimension and allowed visitors to image the specimens they created allowing them to zoom in and see plant parts and structures in further detail to highlight the importance of digitisation. These images can be viewed on the Kew Science Flickr group.

scholarly journals A Workflow for Data Extraction from Digitized Herbarium Specimens

2019 ◽  
Vol 3 ◽  
Author(s):  
Sohaib Younis ◽  
Marco Schmidt ◽  
Bernhard Seeger ◽  
Thomas Hickler ◽  
Claus Weiland
Keyword(s):  
Plant Material ◽  
Data Extraction ◽  
Species Recognition ◽  
Training Data ◽  
Herbarium Specimens ◽  
Plant Organs ◽  
Unseen Data ◽  
Working Groups ◽  
The Many ◽  
Material Extraction

Based on own work on species and trait recognition and complementary studies from other working groups, we present a workflow for data extraction from digitized herbarium specimens using convolutional neural networks. Digitized herbarium sheets contain: preserved plant material as well as additional objects: the label containing information on the collection event, annotations such as revision labels, or notes on material extraction, identifiers such as barcodes or numbers, envelopes for loose plant material and often scale bars and color charts used in the digitization process. preserved plant material as well as additional objects: the label containing information on the collection event, annotations such as revision labels, or notes on material extraction, identifiers such as barcodes or numbers, envelopes for loose plant material and often scale bars and color charts used in the digitization process. In order to treat these objects appropriately, segmentation techniques (Triki et al. 2018) will be applied to localize and identify the different kinds of objects for specific treatments. Detecting presence of plant organs such as leaves, flowers or fruits is already a first step in data extraction potentially useful for phenological studies. Plant organs will be subject to routines for quantitative (Gaikwad et al. 2018) and qualitative (Younis et al. 2018) trait recognition routines. Text-based objects can be treated as described by Kirchhoff et al. 2018, using OCR techniques and considering the many collection-specific terms and abbreviations as described in Schröder 2019. Additionally, species recognition (Younis et al. 2018) will be applied in order to help further identification of incompletely identified collection items or to detect possible misidentifications. All steps described above need sufficient training data including labelling that may be obtained from collection metadata and trait databases. In order to deal with new incoming digitized collections, unseen data or categories, we propose implementation of a new Deep Learning approach, so-called Lifelong Learning: Past knowledge of the network is dynamically saved in latent space using autoencoder and generatively replayed while the network is trained on new tasks which enables it to solve complex image processing tasks without forgetting former knowledge while incrementally learning new classes and knowledge.

State-of-the-Art: A Systematic Literature Review on Image Segmentation in Latent Fingerprint Forensics

2019 ◽  
Vol 12 ◽  
Author(s):  
Megha Chhabra ◽  
Manoj Kumar Shukla ◽  
Kiran Kumar Ravulakollu
Keyword(s):  
Image Segmentation ◽  
Background Noise ◽  
State Of The Art ◽  
Recognition Rate ◽  
Poor Quality ◽  
Latent Fingerprint ◽  
In The Beginning ◽  
The Comparative Study ◽  
Finger Skin

: Latent fingerprints are unintentional finger skin impressions left as ridge patterns at crime scenes. A major challenge in latent fingerprint forensics is the poor quality of the lifted image from the crime scene. Forensics investigators are in permanent search of novel outbreaks of the effective technologies to capture and process low quality image. The accuracy of the results depends upon the quality of the image captured in the beginning, metrics used to assess the quality and thereafter level of enhancement required. The low quality of the image collected by low quality scanners, unstructured background noise, poor ridge quality, overlapping structured noise result in detection of false minutiae and hence reduce the recognition rate. Traditionally, Image segmentation and enhancement is partially done manually using help of highly skilled experts. Using automated systems for this work, differently challenging quality of images can be investigated faster. This survey amplifies the comparative study of various segmentation techniques available for latent fingerprint forensics.

Microwave drying of plant material for herbarium specimens and genetic analysis

Taxon ◽  
2013 ◽  
Vol 62 (4) ◽  
pp. 790-797 ◽  
Author(s):  
Tonya A. Lander ◽  
Bernadeta Dadonaite ◽  
Alex K. Monro
Keyword(s):  
Genetic Analysis ◽  
Plant Material ◽  
Microwave Drying ◽  
Herbarium Specimens

Optimal Scale of Hierarchical Image Segmentation with Scribbles Guidance for Weakly Supervised Semantic Segmentation

2021 ◽  
pp. 2154026
Author(s):  
Zaid Al-Huda ◽  
Donghai Zhai ◽  
Yan Yang ◽  
Riyadh Nazar Ali Algburi
Keyword(s):  
Image Segmentation ◽  
Graphical Model ◽  
Semantic Segmentation ◽  
Saliency Map ◽  
Training Data ◽  
Deep Convolutional Neural Networks ◽  
High Quality ◽  
Optimal Scale ◽  
Supervised Segmentation ◽  
Weakly Supervised

Deep convolutional neural networks (DCNNs) trained on the pixel-level annotated images have achieved improvements in semantic segmentation. Due to the high cost of labeling training data, their applications may have great limitation. However, weakly supervised segmentation approaches can significantly reduce human labeling efforts. In this paper, we introduce a new framework to generate high-quality initial pixel-level annotations. By using a hierarchical image segmentation algorithm to predict the boundary map, we select the optimal scale of high-quality hierarchies. In the initialization step, scribble annotations and the saliency map are combined to construct a graphic model over the optimal scale segmentation. By solving the minimal cut problem, it can spread information from scribbles to unmarked regions. In the training process, the segmentation network is trained by using the initial pixel-level annotations. To iteratively optimize the segmentation, we use a graphical model to refine segmentation masks and retrain the segmentation network to get more precise pixel-level annotations. The experimental results on Pascal VOC 2012 dataset demonstrate that the proposed framework outperforms most of weakly supervised semantic segmentation methods and achieves the state-of-the-art performance, which is [Formula: see text] mIoU.

scholarly journals On Realistically Attacking Tor with Website Fingerprinting

2016 ◽  
Vol 2016 (4) ◽  
pp. 21-36 ◽  
Author(s):  
Tao Wang ◽  
Ian Goldberg
Keyword(s):  
Background Noise ◽  
Laboratory Tests ◽  
Training Data ◽  
Web Traffic ◽  
Training Set ◽  
Data Set ◽  
Laboratory Conditions ◽  
Testing Data ◽  
In The Wild ◽  
New Algorithms

Abstract Website fingerprinting allows a local, passive observer monitoring a web-browsing client’s encrypted channel to determine her web activity. Previous attacks have shown that website fingerprinting could be a threat to anonymity networks such as Tor under laboratory conditions. However, there are significant differences between laboratory conditions and realistic conditions. First, in laboratory tests we collect the training data set together with the testing data set, so the training data set is fresh, but an attacker may not be able to maintain a fresh data set. Second, laboratory packet sequences correspond to a single page each, but for realistic packet sequences the split between pages is not obvious. Third, packet sequences may include background noise from other types of web traffic. These differences adversely affect website fingerprinting under realistic conditions. In this paper, we tackle these three problems to bridge the gap between laboratory and realistic conditions for website fingerprinting. We show that we can maintain a fresh training set with minimal resources. We demonstrate several classification-based techniques that allow us to split full packet sequences effectively into sequences corresponding to a single page each. We describe several new algorithms for tackling background noise. With our techniques, we are able to build the first website fingerprinting system that can operate directly on packet sequences collected in the wild.

scholarly journals Occurrence, Composition and Formation of Ruppia, Widgeon Grass, balls in Saskatchewan Lakes

2005 ◽  
Vol 119 (1) ◽  
pp. 114 ◽  
Author(s):  
Randy W. Olson ◽  
Josef K. Schmutz ◽  
Theodore Hammer
Keyword(s):  
Plant Material ◽  
Saline Lake ◽  
Vascular Plant ◽  
Herbarium Specimens ◽  
Ruppia Maritima ◽  
Washing Machine ◽  
Invertebrate Animal ◽  
Turtle Grass ◽  
Aquatic Vascular Plant ◽  
Near Shore

Widgeon Grass (Ruppia maritima) is an aquatic vascular plant (Ruppiaceae) which has been the source for rare balls of plant material found at the shores of lakes on four continents. In North America, the lakes involved were in North Dakota, Oregon, and now northern and southern Saskatchewan. The formation of the balls has not been observed in nature, but similar balls have been produced in other studies with Posidonia or Turtle Grass (Hydrocharitaceae) fibers under the wavelike action in a washing machine. Our samples are from a saline lake in southern Saskatchewan (49°N), and an over 40-year-old sample from an unknown lake north of the boreal transition zone (52°N). Comparisons of the plant material with herbarium specimens confirm that the balls are almost entirely comprised of Ruppia maritima, with minor items including invertebrate animal parts, sand pebbles and feathers. The context in which the material was found is consistent with the proposition that they are formed by Ruppia inflorescences breaking apart, drifting to near shore due to wind and being rolled into balls by wave action.

scholarly journals Match Feature U-Net: Dynamic Receptive Field Networks for Biomedical Image Segmentation

Symmetry ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 1230
Author(s):  
Xiaofei Qin ◽  
Chengzi Wu ◽  
Hang Chang ◽  
Hao Lu ◽  
Xuedian Zhang
Keyword(s):  
Image Segmentation ◽  
Receptive Field ◽  
Medical Image ◽  
Medical Image Analysis ◽  
Medical Image Segmentation ◽  
Training Data ◽  
Cell Segmentation ◽  
Biomedical Image ◽  
Nuclei Segmentation ◽  
Kernel Convolution

Medical image segmentation is a fundamental task in medical image analysis. Dynamic receptive field is very helpful for accurate medical image segmentation, which needs to be further studied and utilized. In this paper, we propose Match Feature U-Net, a novel, symmetric encoder– decoder architecture with dynamic receptive field for medical image segmentation. We modify the Selective Kernel convolution (a module proposed in Selective Kernel Networks) by inserting a newly proposed Match operation, which makes similar features in different convolution branches have corresponding positions, and then we replace the U-Net’s convolution with the redesigned Selective Kernel convolution. This network is a combination of U-Net and improved Selective Kernel convolution. It inherits the advantages of simple structure and low parameter complexity of U-Net, and enhances the efficiency of dynamic receptive field in Selective Kernel convolution, making it an ideal model for medical image segmentation tasks which often have small training data and large changes in targets size. Compared with state-of-the-art segmentation methods, the number of parameters in Match Feature U-Net (2.65 M) is 34% of U-Net (7.76 M), 29% of UNet++ (9.04 M), and 9.1% of CE-Net (29 M). We evaluated the proposed architecture in four medical image segmentation tasks: nuclei segmentation in microscopy images, breast cancer cell segmentation, gland segmentation in colon histology images, and disc/cup segmentation. Our experimental results show that Match Feature U-Net achieves an average Mean Intersection over Union (MIoU) gain of 1.8, 1.45, and 2.82 points over U-Net, UNet++, and CE-Net, respectively.

scholarly journals Clouds Classification from Sentinel-2 Imagery with Deep Residual Learning and Semantic Image Segmentation

2019 ◽  
Vol 11 (2) ◽  
pp. 119 ◽  
Author(s):  
Cheng-Chien Liu ◽  
Yu-Cheng Zhang ◽  
Pei-Yin Chen ◽  
Chien-Chih Lai ◽  
Yi-Hsin Chen ◽  
...  
Keyword(s):  
Image Segmentation ◽  
Change Detection ◽  
Data Augmentation ◽  
Satellite Image ◽  
Training Data ◽  
Training Dataset ◽  
Standard Size ◽  
Semantic Image Segmentation ◽  
Residual Learning ◽  
Sentinel 2

Detecting changes in land use and land cover (LULC) from space has long been the main goal of satellite remote sensing (RS), yet the existing and available algorithms for cloud classification are not reliable enough to attain this goal in an automated fashion. Clouds are very strong optical signals that dominate the results of change detection if they are not removed completely from imagery. As various architectures of deep learning (DL) have been proposed and advanced quickly, their potential in perceptual tasks has been widely accepted and successfully applied to many fields. A comprehensive survey of DL in RS has been reviewed, and the RS community has been suggested to be leading researchers in DL. Based on deep residual learning, semantic image segmentation, and the concept of atrous convolution, we propose a new DL architecture, named CloudNet, with an enhanced capability of feature extraction for classifying cloud and haze from Sentinel-2 imagery, with the intention of supporting automatic change detection in LULC. To ensure the quality of the training dataset, scene classification maps of Taiwan processed by Sen2cor were visually examined and edited, resulting in a total of 12,769 sub-images with a standard size of 224 × 224 pixels, cut from the Sen2cor-corrected images and compiled in a trainset. The data augmentation technique enabled CloudNet to have stable cirrus identification capability without extensive training data. Compared to the traditional method and other DL methods, CloudNet had higher accuracy in cloud and haze classification, as well as better performance in cirrus cloud recognition. CloudNet will be incorporated into the Open Access Satellite Image Service to facilitate change detection by using Sentinel-2 imagery on a regular and automatic basis.

Sign in / Sign up

Export Citation Format

Share Document