{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Nanocrystal Segmentation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This notebook demonstrates two approaches to nanocrystal segmentation:\n",
"1. Virtual dark-field (VDF) imaging-based segmentation\n",
"2. Non-negative matrix factorisation (NMF)-based segmentation\n",
"\n",
"The segmentation is demonstrated on a SPED dataset of partly overlapping MgO nanoparticles, where some of the particles share the same orientation."
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"This functionality has been checked to run with pyxem-0.15.0 (April 2023). Bugs are always possible, do not trust the code blindly, and if you experience any issues please report them here: https://github.com/pyxem/pyxem-demos/issues"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Contents"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"1. Setting up, Loading Data, Pre-processing\n",
"2. Virtual Image Based Segmentation\n",
"3. NMF Based Segmentation"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Setting up, Loading Data, Pre-processing"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Import pyxem and other required libraries"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"WARNING:silx.opencl.common:The module pyOpenCL has been imported but can't be used here\n"
]
}
],
"source": [
"%matplotlib inline\n",
"import numpy as np\n",
"import hyperspy.api as hs\n",
"import matplotlib.pyplot as plt\n",
"import pyxem as pxm"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Load demonstration data"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/cssfrancis/hyperspy-bundle/lib/python3.10/site-packages/hyperspy/misc/utils.py:471: VisibleDeprecationWarning: Use of the `binned` attribute in metadata is going to be deprecated in v2.0. Set the `axis.is_binned` attribute instead. \n",
" warnings.warn(\n",
"/home/cssfrancis/hyperspy-bundle/lib/python3.10/site-packages/hyperspy/io.py:572: VisibleDeprecationWarning: Loading old file version. The binned attribute has been moved from metadata.Signal to axis.is_binned. Setting this attribute for all signal axes instead.\n",
" warnings.warn('Loading old file version. The binned attribute '\n"
]
}
],
"source": [
"dp = hs.load('./data/06/mgo_nanoparticles.hdf5', reader=\"hspy\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Set the Calibrations..."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"scale = 0.03246*2 \n",
"scale_real = 3.03*2\n",
"dp.set_diffraction_calibration(scale)\n",
"dp.set_scan_calibration(scale_real)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Plot data to inspect"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"