Struct BaseRecLabelDecode 

pub struct BaseRecLabelDecode { /* private fields */ }

A base decoder for text recognition that handles character mapping and basic decoding operations.

This struct is responsible for converting model predictions into readable text strings. It maintains a character dictionary for mapping indices to characters and provides methods for decoding text with optional duplicate removal and confidence scoring.

Fields

• reverse - Flag indicating whether to reverse the text output
• dict - A mapping from characters to their indices in the character list
• character - A list of characters in the vocabulary, indexed by their position

Implementations

impl BaseRecLabelDecode

pub fn new( character_str: Option<&str>, use_space_char: bool, ) -> BaseRecLabelDecode

Creates a new BaseRecLabelDecode instance.

Arguments

• character_str - An optional string containing the character vocabulary. If None, a default alphanumeric character set is used.
• use_space_char - Whether to include a space character in the vocabulary.

Returns

A new BaseRecLabelDecode instance.

pub fn from_string_list( character_list: Option<&[String]>, use_space_char: bool, ) -> BaseRecLabelDecode

Creates a new BaseRecLabelDecode instance from a list of strings.

Arguments

• character_list - An optional slice of strings containing the character vocabulary. Only the first character of each string is used. If None, a default alphanumeric character set is used.
• use_space_char - Whether to include a space character in the vocabulary.

Returns

A new BaseRecLabelDecode instance.

pub fn decode( &self, text_index: &[Vec<usize>], text_prob: Option<&[Vec<f32>]>, is_remove_duplicate: bool, ) -> Vec<(String, f32)>

Decodes model predictions into text strings with confidence scores.

Arguments

• text_index - A slice of vectors containing the predicted character indices.
• text_prob - An optional slice of vectors containing the prediction probabilities.
• is_remove_duplicate - Whether to remove consecutive duplicate characters.

Returns

A vector of tuples, each containing a decoded text string and its confidence score.

pub fn apply( &self, pred: &ArrayBase<OwnedRepr<f32>, Dim<[usize; 3]>>, ) -> (Vec<String>, Vec<f32>)

Applies the decoder to a tensor of model predictions.

Arguments

• pred - A 3D tensor containing the model predictions.

Returns

A tuple containing:

• A vector of decoded text strings
• A vector of confidence scores for each text string