Blocked Images

Read and navigate big images and multiresolution images

A big image may not fit into memory, which makes it challenging to display and process. The blockedImage object solves this problem by representing an image as a collection of smaller blocks of data that can be independently loaded and processed. A blockedImage object can support large images and images with one or multiple resolution levels.

Functions

expand all

Create Blocked Images

`blockedImage`	Big or multiresolution image made from discrete blocks
`makeMultiLevel2D`	2-D multilevel blocked image
`makeMultiLevel3D`	3-D multilevel blocked image
`concatenateLevels`	Concatenate levels from multiple blocked images
`polyToBlockedImage`	Create labeled `blockedImage` object from set of ROIs

Select Blocks

`blockLocationSet`	List of block locations in large images
`selectBlockLocations`	Select blocks from blocked images
`mergeBlockLocationSets`	Merge block location sets

Display Blocked Images

`bigimageshow`	Display 2-D `blockedImage` object
`showmask`	Show mask overlay at specified inclusion threshold
`showlabels`	Display label overlay on `bigimageshow` object

Process Blocked Images

`apply`	Process blocks of blocked image
`countEachLabel`	Counts number of pixel labels for each class
`crop`	Create cropped version of blocked image
`blockedImageDatastore`	Datastore for use with blocks from `blockedImage` objects

Topics

Set Up Spatial Referencing for Blocked Images
This example shows how to set up and verify the spatial referencing information of a blockedImage object.
Read Whole-Slide Images with Custom Blocked Image Adapter
This example shows how to add support for reading whole-slide images by creating a custom blocked image adapter.
Label Large Images in the Image Labeler (Computer Vision Toolbox)
This section describes the differences with using the Image Labeler app with blocked images.
Convert Image Labeler Polygons to Labeled Blocked Image for Semantic Segmentation
This example shows how to convert polygon labels stored in a groundTruth object into a labeled blocked image suitable for semantic segmentation workflows.
Work with Blocked Images Using Volume Segmenter
Segment a volumetric image that could be too large to fit into memory by converting the volume to a blocked image.

Featured Examples

Process Blocked Images Efficiently Using Partial Images or Lower Resolutions

Process a blocked image quickly using two strategies that enable computations on smaller representative samples of the high-resolution image.

Open Live Script

Process Blocked Images Efficiently Using Mask

Process a blocked image efficiently by using a mask to isolate regions of interest (ROIs).

Open Live Script

Create Labeled Blocked Image from ROIs and Masks

Create a labeled blocked image from a set of ROIs.

Open Live Script

Detect and Count Cell Nuclei in Whole Slide Images

Use color thresholding and region property analysis, while working with small blocks of image data, to detect nuclei in WSIs.

Open Live Script

Preprocess Multiresolution Images for Training Classification Network

Prepare datastores that read and preprocess multiresolution whole slide images (WSIs) that might not fit in memory.

Open Live Script

Classify Tumors in Multiresolution Blocked Images

Classify multiresolution whole slide images (WSIs) that might not fit in memory using an Inception-v3 deep neural network.

Open Live Script

Explore Blocked Image Details with Interactive ROIs

Display a detailed region of a blocked image selected interactively using ROI tools.

Open Script

Warp Blocked Image at Coarse and Fine Resolution Levels

Apply a geometric transformation (warping) to a blocked image.

Open Live Script